Article(id=1322961414566064491, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, articleNumber=null, orderNo=null, doi=10.11834/jig.260216, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1776268800000, receivedDateStr=2026-04-16, revisedDate=1779120000000, revisedDateStr=2026-05-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348180666, onlineDateStr=2026-10-30, pubDate=1789488000000, pubDateStr=2026-09-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348180666, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348180666, creator=13701087609, updateTime=1793348180666, updator=13701087609, issue=Issue{id=1322961355078246774, tenantId=1146029695717560320, journalId=1249024232475115590, year='2026', volume='31', issue='9', pageStart='3075', pageEnd='3440', issueExtLink='null', onlineDate='null', pubDate='1789488000000', pubDateStr='2026-09-16', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793348166484, creator='13701087609', updateTime=1793348617535, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322963246994555810, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322963246998750115, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=3227, endPage=3250, ext={EN=ArticleExt(id=1322961414956134765, articleId=1322961414566064491, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=Artificial intelligence-assisted flight technologies for single-pilot operations: a comprehensive review, columnId=1322961355891941751, journalTitle=Journal of Image and Graphics, columnName=The intelligent empowerment of large models in the aviation field, runingTitle=null, highlight=null, articleAbstract=

Today,the aviation industry faces a critical shortage of qualified pilots and escalating labor costs due to the continuous surge in global air transport demand. Consequently,single-pilot operation (SPO) has emerged as a strategic evolution in civil aviation to optimize crew resources and mitigate pilot fatigue,especially during long-haul flights. However,the transition from traditional multicrew cockpits to a single-pilot environment is not merely a reduction in personnel; rather,it introduces a significant “cognitive and decision-making gap” previously filled by the co-pilot. To bridge this gap,this paper proposes the concept of the “AI co-pilot” —— an intelligent system designed to establish a deep cognitive collaborative relationship with the human pilot through advanced perception,semantic understanding,and autonomous decision-making capabilities. This paper provides a systematic and comprehensive review of the core technological components enabling AI-assisted piloting. In this work,we propose a four-layer analytical framework known as “perception-cognition-interaction-decision-safety monitoring”. This structure serves as a blueprint for integrating heterogeneous AI modules into the high-integrity environment of an aircraft cockpit. First,we look into multimodal physiological and behavioral sensing technologies that are essential for the real-time monitoring of a pilot’s workload and fatigue state. Given that traditional subjective assessments are insufficient for high-dynamic flight environments,this review focuses on the integration of electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS). In particular,we provide a critical analysis of their trade-offs: while EEG offers superior temporal resolution capable of capturing instantaneous cognitive shifts,fNIRS demonstrates stronger robustness against motion artifacts in a vibrating cockpit. Furthermore,computer vision (CV) techniques are discussed for the nonintrusive monitoring of facial expressions,percentage of eyelid closure (PERCLOS),and visual tunneling effects. The fusion of these modalities allows the AI Co-pilot to “read” the pilot’s state and trigger adaptive automation upon detection of cognitive overload. Second,the review explores intelligent speech interaction and semantic understanding within the complex controller-pilot data link communications (CPDLC) and radio environments. The aviation context poses unique challenges,including low signal-to-noise ratios in VHF communications and nonstandard accents. In this paper,we analyze the application of LLMs and transformer-based architectures in intent recognition and slot filling for air traffic control (ATC) instructions. By parsing complex,nested instructions into executable parameters,the AI Co-pilot functions as an “intelligent radio operator” that significantly reduces the auditory and manual workload of the single pilot. Third,we summarize intelligent route planning and dynamic conflict resolution driven by the synergy of large models and deep reinforcement learning (DRL). Algorithms such as proximal policy optimization (PPO) and soft actor-critic (SAC) are evaluated for their efficacy in continuous action spaces and high-dimensional flight dynamics. Unlike traditional rule-based flight management systems (FMS),AI-driven planners can explore optimal trajectories in unconstrained airspace and respond adaptively to extreme weather or system failures. Additionally,we emphasize the transition from individual agent optimization to multiagent reinforcement learning (MARL) for collaborative collision avoidance in dense urban air mobility (UAM) scenarios. A significant portion of this review is dedicated to the core barriers that hinder the commercial deployment of aviation AI. We provide an in-depth analysis of the non-interpretability of “black-box” deep learning models,which prevents human pilots from establishing calibrated trust during time-critical emergencies. Furthermore,the paradigm conflict between the nondeterministic nature of AI and traditional deterministic airworthiness standards (e.g.,DO-178C) is dissected. We also discuss the latest policy trends from EASA and the FAA,highlighting the shift toward “run-time assurance (RTA)” frameworks. Specifically,RTA acts as a safety shield,bounding the outputs of complex AI models within a predefined safe flight envelope and ultimately providing a viable certification pathway. Finally,this paper presents a perspective on future trends. We posit that the next generation of aviation AI will evolve toward a “multimodal unified architecture” in which text,speech,vision,and flight dynamics are aligned in a single latent space. We predict that this evolution will transform the AI Co-pilot from a collection of isolated subtasks into a holistic “cognitive partner”. By emphasizing transparency,bidirectional communication,and standardized certification,this review aims to provide a theoretical foundation and engineering reference for achieving high-transparency,deep human-machine collaborative intelligent cockpits in the SPO era.

, authors=Lin Yuan1, Yang Li2, 3, Yanfei Miao4, Xiaoyang Li5, Congqi Cao1, *, authorsList=Lin Yuan, Yang Li, Yanfei Miao, Xiaoyang Li, Congqi Cao, authorCompany=null, correspAuthors=Congqi Cao, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322961418668093816, articleId=1322961414566064491, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=人工智能辅助的单机长飞行驾驶技术综述, columnId=1322961356168765817, journalTitle=中国图象图形学报, columnName=大模型在航空领域的智慧赋能, runingTitle=null, highlight=null, articleAbstract=

随着全球航空运输需求持续增长,单机长体制(single-pilot operation,SPO)成为民航领域应对飞行员短缺与人力成本攀升的核心发展方向。然而,从双人机组向单人驾驶的转变,核心瓶颈在于如何填补缺失副驾驶后产生的认知与决策空缺。“AI(artificial intelligence)副驾驶”概念的提出,旨在通过具备深度感知、语义理解与自主决策能力的智能系统,与人类飞行员构建认知型协作关系。本文系统梳理了人工智能辅助飞行驾驶的关键技术,构建了“感知—认知—推理—交互决策—安全监控”的系统分析框架。重点阐述了基于脑电图(electroencephalogram,EEG)、功能性近红外光谱(functional near-infrared spectroscopy,fNIRS)以及计算机视觉的多模态生理行为感知技术,分析了其在实时监测飞行员负荷与疲劳状态方面的最新进展。同时,针对复杂的陆空通话环境,探讨了基于大模型架构的空管指令意图识别与语义提取技术。此外,本文还归纳了大模型与深度强化学习协同驱动的智能航路规划与冲突解算方法,并深入剖析了当前阻碍AI技术商业化落地的核心壁垒,包括深度学习模型的不可解释性、人机信任机制的缺失以及非确定性智能系统的适航认证困境。最后,本文指出大模型驱动的多模态统一架构与运行时保障适航路径是未来航空人工智能发展的关键方向,旨在为实现高透明度、深层人机协同的智能驾驶舱提供参考。

, authors=袁林1, 李阳2, 3, 苗延飞4, 李枭扬5, 曹聪琦1, *, authorsList=袁林, 李阳, 苗延飞, 李枭扬, 曹聪琦, authorCompany=null, correspAuthors=曹聪琦, authorNote=

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

, correspAuthorsNote=
曹聪琦
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=4UPPw2mYFIcixucvHNrwXA==, magXml=kXl+JhmdSTE9yChpCuaA/Q==, pdfUrl=null, pdf=2OjSQwKhwoEatoNntg/uDQ==, pdfFileSize=2486697, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jKT8HUxKPrM6xxWCCdv4lg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=W7biaECM7jwYmnZ/6G/mLg==, mapNumber=null, fund=null)}, authors=[Author(id=1322961419326599561, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lin.y@mail.nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419406291339, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419326599561, language=EN, stringName=Lin Yuan, firstName=Lin, middleName=null, lastName=Yuan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419477594508, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419326599561, language=CN, stringName=袁林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西北工业大学计算机学院,西安 710129, bio={"content":"

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

"}, bioImg=null, bioContent=

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418890391929, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=1, ext=[AuthorCompanyExt(id=1322961418898780538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961418911363451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学计算机学院,西安 710129)])]), Author(id=1322961419553091982, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tianciyang2010@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419636978065, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419553091982, language=EN, stringName=Yang Li, firstName=Yang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China
3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419704086930, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419553091982, language=CN, stringName=李阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 沈阳飞机设计研究所,沈阳 110035
3 西北工业大学卓越工程师学院,西安 710072, bio={"content":"

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

"}, bioImg=null, bioContent=

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418970083708, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=2, ext=[AuthorCompanyExt(id=1322961418978472317, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China), AuthorCompanyExt(id=1322961418991055230, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 沈阳飞机设计研究所,沈阳 110035)]), AuthorCompany(id=1322961419066552703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=3, ext=[AuthorCompanyExt(id=1322961419074941312, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China), AuthorCompanyExt(id=1322961419083329921, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西北工业大学卓越工程师学院,西安 710072)])]), Author(id=1322961419779584404, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=miaoyf20@mails.tsinghua.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419871859094, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419779584404, language=EN, stringName=Yanfei Miao, firstName=Yanfei, middleName=null, lastName=Miao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419938967959, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419779584404, language=CN, stringName=苗延飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 清华大学航天航空学院,北京 100084, bio={"content":"

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

"}, bioImg=null, bioContent=

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961419142050178, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=4, ext=[AuthorCompanyExt(id=1322961419150438787, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China), AuthorCompanyExt(id=1322961419158827396, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 清华大学航天航空学院,北京 100084)])]), Author(id=1322961420006076825, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lixiaoyang@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961421675409819, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961420006076825, language=EN, stringName=Xiaoyang Li, firstName=Xiaoyang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961421755101596, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961420006076825, language=CN, stringName=李枭扬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 西北工业大学电子信息学院,西安 710129, bio={"content":"

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

"}, bioImg=null, bioContent=

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961419230130565, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=5, ext=[AuthorCompanyExt(id=1322961419242713478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961419251102087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学电子信息学院,西安 710129)])]), Author(id=1322961421855764894, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=congqi.cao@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961421935456672, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961421855764894, language=EN, stringName=Congqi Cao, firstName=Congqi, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961422027731361, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961421855764894, language=CN, stringName=曹聪琦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 西北工业大学计算机学院,西安 710129, bio={"content":"

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

"}, bioImg=null, bioContent=

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418890391929, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=1, ext=[AuthorCompanyExt(id=1322961418898780538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961418911363451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学计算机学院,西安 710129)])])], keywords=[Keyword(id=1322961422145171874, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, orderNo=1, keyword=artificial intelligence (AI)), Keyword(id=1322961422224863651, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, orderNo=2, keyword=AI co-pilot), Keyword(id=1322961422291972516, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, orderNo=3, keyword=pilot state awareness), Keyword(id=1322961422350692773, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, orderNo=4, keyword=intelligent speech interaction), Keyword(id=1322961422430384550, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, orderNo=5, keyword=deep reinforcement learning), Keyword(id=1322961422518464935, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, orderNo=1, keyword=人工智能(AI)), Keyword(id=1322961422593962408, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, orderNo=2, keyword=AI副驾驶), Keyword(id=1322961422677848489, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, orderNo=3, keyword=飞行员状态感知), Keyword(id=1322961422740763050, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, orderNo=4, keyword=智能语音交互), Keyword(id=1322961422807871915, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, orderNo=5, keyword=深度强化学习(DRL))], refs=[Reference(id=1322961424091328952, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=3, issue=1, pageStart=null, pageEnd=100013, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Ahmed W, journalName=Premier Journal of Artificial Intelligence, refType=null, unstructuredReference=Ahmed W. 2025. Artificial intelligence in aviation: a review of machine learning and deep learning applications for enhanced safety and security. Premier Journal of Artificial Intelligence,3(1): #100013 [DOI: 10.70389/PJAI.100013], articleTitle=Artificial intelligence in aviation: a review of machine learning and deep learning applications for enhanced safety and security, refAbstract=null), Reference(id=1322961424171020729, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=null, pageStart=5132, pageEnd=5150, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Alreshidi I, Moulitsas I, Jenkins K W, journalName=IEEE Access, refType=null, unstructuredReference=Alreshidi I,Moulitsas I and Jenkins K W. 2024. Advancing aviation safety through machine learning and psychophysiological data: a systematic review. IEEE Access,12: 5132-5150 [DOI: 10.1109/ACCESS.2024.3349495], articleTitle=Advancing aviation safety through machine learning and psychophysiological data: a systematic review, refAbstract=null), Reference(id=1322961424250712506, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=339, issue=20, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Arteaga R A, journalName=U, refType=null, unstructuredReference=Arteaga R A. 2024. Artificial intelligence co-pilot for manned and unmanned aircraft. U.S.,No. 20,240,339,039, articleTitle=Artificial intelligence co-pilot for manned and unmanned aircraft, refAbstract=null), Reference(id=1322961424359764411, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2022, volume=2676, issue=1, pageStart=798, pageEnd=810, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Badrinath S, Balakrishnan H, journalName=Transportation Research Record: Journal of the Transportation Research Board, refType=null, unstructuredReference=Badrinath S and Balakrishnan H. 2022. Automatic speech recognition for air traffic control communications. Transportation Research Record: Journal of the Transportation Research Board,2676(1): 798-810 [DOI: 10.1177/03611981211036359], articleTitle=Automatic speech recognition for air traffic control communications, refAbstract=null), Reference(id=1322961424439456188, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=57, issue=1, pageStart=null, pageEnd=17, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Banerjee C, Nguyen K, Fookes C, George K, journalName=ACM Computing Surveys, refType=null, unstructuredReference=Banerjee C,Nguyen K,Fookes C and George K. 2025. Physics-informed computer vision: a review and perspectives. ACM Computing Surveys,57(1): #17 [DOI: 10.1145/3689037], articleTitle=Physics-informed computer vision: a review and perspectives, refAbstract=null), Reference(id=1322961426117177789, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=1991, volume=6, issue=3, pageStart=18, pageEnd=29, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Banks S B, Lizza C S, journalName=IEEE Expert, refType=null, unstructuredReference=Banks S B and Lizza C S. 1991. Pilot’s associate: a cooperative,knowledge-based system application. IEEE Expert,6(3): 18-29 [DOI: 10.1109/64.87681], articleTitle=Pilot’s associate: a cooperative,knowledge-based system application, refAbstract=null), Reference(id=1322961426201063870, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=1991, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Billings C E, journalName=NASA Ames Research Center, refType=null, unstructuredReference=Billings C E. 1991. Human-centered aircraft automation: a concept and guidelines. NASA Ames Research Center, articleTitle=Human-centered aircraft automation: a concept and guidelines, refAbstract=null), Reference(id=1322961426284949951, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2003.08353.pdf, language=null, rfNumber=null, rfOrder=7, authorNames=Brittain M, Yang X X, Wei P, journalName=null, refType=null, unstructuredReference=Brittain M,Yang X X and Wei P. 2020. A deep multi-agent reinforcement learning approach to autonomous separation assurance [EB/OL]. [2026-04-16]., articleTitle=A deep multi-agent reinforcement learning approach to autonomous separation assurance, refAbstract=null), Reference(id=1322961426377224640, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=#3412, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Chen J W, Liu Y M, Cooke N, Tang P B, journalName=Proceedings of 2019 AIAA Aviation Forum, refType=null, unstructuredReference=Chen J W,Liu Y M,Cooke N and Tang P B. 2019. Real-time facial expression and head pose analysis for monitoring the workloads of air traffic controllers//Proceedings of 2019 AIAA Aviation Forum. Dallas,USA: AIAA: #3412 [DOI: 10.2514/6.2019-3412], articleTitle=Real-time facial expression and head pose analysis for monitoring the workloads of air traffic controllers, refAbstract=null), Reference(id=1322961426461110721, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2014, volume=44, issue=1, pageStart=13, pageEnd=29, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Chen J Y C, Barnes M J, journalName=IEEE Transactions on Human-Machine Systems, refType=null, unstructuredReference=Chen J Y C and Barnes M J. 2014. Human-agent teaming for multirobot control: a review of human factors issues. IEEE Transactions on Human-Machine Systems,44(1): 13-29 [DOI: 10.1109/THMS.2013.2293535], articleTitle=Human-agent teaming for multirobot control: a review of human factors issues, refAbstract=null), Reference(id=1322961426524025282, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=14, issue=null, pageStart=null, pageEnd=724, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Chen W L, Wagner J, Heugel N, Sugar J, Lee Y W, Conant L, journalName=Frontiers in Neuroscience, refType=null, unstructuredReference=Chen W L,Wagner J,Heugel N,Sugar J,Lee Y W,Conant L,et al. 2020. Functional near-infrared spectroscopy and its clinical application in the field of neuroscience: advances and future directions. Frontiers in Neuroscience,14: #724 [DOI: 10.3389/fnins.2020.00724], articleTitle=Functional near-infrared spectroscopy and its clinical application in the field of neuroscience: advances and future directions, refAbstract=null), Reference(id=1322961426599522755, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=117984, pageEnd=118001, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Chronis C, Anagnostopoulos G, Politi E, Dimitrakopoulos G, Varlamis I, journalName=IEEE Access, refType=null, unstructuredReference=Chronis C,Anagnostopoulos G,Politi E,Dimitrakopoulos G and Varlamis I. 2023. Dynamic navigation in unconstrained environments using reinforcement learning algorithms. IEEE Access,11: 117984-118001 [DOI: 10.1109/ACCESS.2023.3326435], articleTitle=Dynamic navigation in unconstrained environments using reinforcement learning algorithms, refAbstract=null), Reference(id=1322961426666631620, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2004, volume=null, issue=null, pageStart=#5257, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Crum V, Homan D, Bortner R, journalName=null, refType=null, unstructuredReference=Crum V,Homan D and Bortner R. 2004. Certification challenges for autonomous flight control systems//Proceedings of 2004 AIAA Guidance,Navigation,and Control Conference and Exhibit. Providence,USA: AIAA: #5257 [DOI: 10.2514/6.2004-5257], articleTitle=Certification challenges for autonomous flight control systems, refAbstract=null), Reference(id=1322961426737934789, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=119, pageEnd=140, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Cummings M L, Britton D, journalName=Living With Robots, refType=null, unstructuredReference=Cummings M L and Britton D. 2020. Regulating safety-critical autonomous systems: past,present,and future perspectives//Pak R,de Visser E J and Rovira E,eds. Living With Robots. Amsterdam: Elsevier: 119-140 [DOI: 10.1016/B978-0-12-815367-3.00006-2], articleTitle=Regulating safety-critical autonomous systems: past,present,and future perspectives, refAbstract=null), Reference(id=1322961426800849350, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=12, pageStart=1014, pageEnd=1024, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Davidoff A, Vonderhaar L, Caldwell A, Procko T, Ochoa O, journalName=Journal of Aerospace Information Systems, refType=null, unstructuredReference=Davidoff A,Vonderhaar L,Caldwell A,Procko T and Ochoa O. 2024. Role,needs,and state of cognitive assistants in single-pilot operations. Journal of Aerospace Information Systems,21(12): 1014-1024 [DOI: 10.2514/1.I011432], articleTitle=Role,needs,and state of cognitive assistants in single-pilot operations, refAbstract=null), Reference(id=1322961426867958215, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=3, pageStart=1542, pageEnd=1555, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Debie E, Rojas R F, Fidock J, Barlow M, Kasmarik K, Anavatti S, journalName=IEEE Transactions on Cybernetics, refType=null, unstructuredReference=Debie E,Rojas R F,Fidock J,Barlow M,Kasmarik K,Anavatti S,et al. 2021. Multimodal fusion for objective assessment of cognitive workload: a review. IEEE Transactions on Cybernetics,51(3): 1542-1555 [DOI: 10.1109/TCYB.2019.2939399], articleTitle=Multimodal fusion for objective assessment of cognitive workload: a review, refAbstract=null), Reference(id=1322961426939261384, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=3, pageStart=null, pageEnd=1295, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Degas A, Islam M R, Hurter C, Barua S, Rahman H, Poudel M, journalName=Applied Sciences, refType=null, unstructuredReference=Degas A,Islam M R,Hurter C,Barua S,Rahman H,Poudel M,et al. 2022. A survey on artificial intelligence (AI) and explainable AI in air traffic management: current trends and development with future research trajectory. Applied Sciences,12(3): #1295 [DOI: 10.3390/app12031295], articleTitle=A survey on artificial intelligence (AI) and explainable AI in air traffic management: current trends and development with future research trajectory, refAbstract=null), Reference(id=1322961427006370249, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Deng Q H, Yang Y, Zhang X X, Qian S S, Zhang M H, Cai K Q, journalName=null, refType=null, unstructuredReference=Deng Q H,Yang Y,Zhang X X,Qian S S,Zhang M H and Cai K Q. 2023. A BERT-based intent recognition and slot filling joint model for air traffic control instruction understanding//Proceedings of the 42nd IEEE/AIAA Digital Avionics Systems Conference. Barcelona,Spain: IEEE: 1-9 [DOI: 10.1109/DASC58513.2023.10311266], articleTitle=A BERT-based intent recognition and slot filling joint model for air traffic control instruction understanding, refAbstract=null), Reference(id=1322961427073479114, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=3, pageStart=229, pageEnd=246, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Durach C F, Gutierrez L, journalName=International Journal of Physical Distribution and Logistics Management, refType=null, unstructuredReference=Durach C F and Gutierrez L. 2024. “Hello,this is your AI co-pilot”—operational implications of artificial intelligence chatbots. International Journal of Physical Distribution and Logistics Management,54(3): 229-246 [DOI: 10.1108/IJPDLM-01-2024-0031], articleTitle=“Hello,this is your AI co-pilot”—operational implications of artificial intelligence chatbots, refAbstract=null), Reference(id=1322961427148976587, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=4, issue=2, pageStart=67, pageEnd=94, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Dzreke S S, journalName=International Journal of Management Science and Application, refType=null, unstructuredReference=Dzreke S S. 2025. The AI co-pilot: navigating market turbulence and charting a course for sustainable advantage. International Journal of Management Science and Application,4(2): 67-94 [DOI: 10.58291/ijmsa.v4i2.442], articleTitle=The AI co-pilot: navigating market turbulence and charting a course for sustainable advantage, refAbstract=null), Reference(id=1322961427232862668, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2017a, volume=59, issue=1, pageStart=5, pageEnd=27, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Endsley M R, journalName=Human Factors: The Journal of the Human Factors and Ergonomics Society, refType=null, unstructuredReference=Endsley M R. 2017a. From here to autonomy: lessons learned from human — automation research. Human Factors: The Journal of the Human Factors and Ergonomics Society,59(1): 5-27 [DOI: 10.1177/0018720816681350], articleTitle=From here to autonomy: lessons learned from human — automation research, refAbstract=null), Reference(id=1322961427312554445, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2017b, volume=null, issue=null, pageStart=9, pageEnd=42, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Endsley M R, journalName=Situational Awareness, refType=null, unstructuredReference=Endsley M R. 2017b. Toward a theory of situation awareness in dynamic systems//Salas E,ed. Situational Awareness. London: Routledge: 9-42, articleTitle=Toward a theory of situation awareness in dynamic systems, refAbstract=null), Reference(id=1322961427388051918, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Estival D, Farris C, Molesworth B, journalName=Aviation English: A Lingua Franca for Pilots and Air Traffic Controllers, refType=null, unstructuredReference=Estival D,Farris C and Molesworth B. 2016. Aviation English: A Lingua Franca for Pilots and Air Traffic Controllers. London: Routledge [DOI: 10.4324/9781315661179s], articleTitle=null, refAbstract=null), Reference(id=1322961427547435471, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=2149, pageEnd=2163, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Flores A, Paselk A, McAndrew I, journalName=null, refType=null, unstructuredReference=Flores A,Paselk A and McAndrew I. 2024. Advancing perspectives: a scoping review of artificial intelligence applications in aviation human factors for flight crews//Proceedings of 2024 AHFE International Conference on Human Factors in Design,Engineeing,and Conputing. Hawaii,USA: AHFE International: 2149-2163 [DOI: 10.54941/ahfe1005783], articleTitle=Advancing perspectives: a scoping review of artificial intelligence applications in aviation human factors for flight crews, refAbstract=null), Reference(id=1322961427627127248, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2018, volume=12, issue=null, pageStart=null, pageEnd=187, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Gateau T, Ayaz H, Dehais F, journalName=Frontiers in Human Neuroscience, refType=null, unstructuredReference=Gateau T,Ayaz H and Dehais F. 2018. In silico vs. over the clouds: on-the-fly mental state estimation of aircraft pilots,using a functional near infrared spectroscopy based passive-BCI. Frontiers in Human Neuroscience,12: #187 [DOI: 10.3389/fnhum.2018.00187], articleTitle=In silico vs. over the clouds: on-the-fly mental state estimation of aircraft pilots,using a functional near infrared spectroscopy based passive-BCI, refAbstract=null), Reference(id=1322961427706819025, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=69, issue=1, pageStart=140, pageEnd=150, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Gui G, Liu F, Sun J L, Yang J, Zhou Z Q, Zhao D X, journalName=IEEE Transactions on Vehicular Technology, refType=null, unstructuredReference=Gui G,Liu F,Sun J L,Yang J,Zhou Z Q and Zhao D X. 2020. Flight delay prediction based on aviation big data and machine learning. IEEE Transactions on Vehicular Technology,69(1): 140-150 [DOI: 10.1109/TVT.2019.2954094], articleTitle=Flight delay prediction based on aviation big data and machine learning, refAbstract=null), Reference(id=1322961427912339922, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=2, pageStart=44, pageEnd=58, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=Gunning D, Aha D W, journalName=AI Magazine, refType=null, unstructuredReference=Gunning D and Aha D W. 2019. DARPA’s explainable artificial intelligence program. AI Magazine,40(2): 44-58 [DOI: 10.1609/aimag.v40i2.2850], articleTitle=DARPA’s explainable artificial intelligence program, refAbstract=null), Reference(id=1322961427992031699, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1861, pageEnd=1870, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Haarnoja T, Zhou A, Abbeel P, Levine S, journalName=null, refType=null, unstructuredReference=Haarnoja T,Zhou A,Abbeel P and Levine S. 2018. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor//Proceedings of the 35th International Conference on Machine Learning. Stockholm,Sweden: PMLR: 1861-1870, articleTitle=Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor, refAbstract=null), Reference(id=1322961428109472212, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Hafner D, Lillicrap T, Ba J, Norouzi M, journalName=null, refType=null, unstructuredReference=Hafner D,Lillicrap T,Ba J and Norouzi M. 2020. Dream to control: learning behaviors by latent imagination//Proceedings of the 8th International Conference on Learning Representations. Addis Ababa,Ethiopia: OpenReview.net, articleTitle=Dream to control: learning behaviors by latent imagination, refAbstract=null), Reference(id=1322961428180775381, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2007, volume=79, issue=5, pageStart=518, pageEnd=526, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Harris D, journalName=Aircraft Engineering and Aerospace Technology, refType=null, unstructuredReference=Harris D. 2007. A human-centred design agenda for the development of single crew operated commercial aircraft. Aircraft Engineering and Aerospace Technology,79(5): 518-526 [DOI: 10.1108/00022660710780650], articleTitle=A human-centred design agenda for the development of single crew operated commercial aircraft, refAbstract=null), Reference(id=1322961428247884246, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=127, issue=1313, pageStart=1171, pageEnd=1191, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=Harris D, journalName=The Aeronautical Journal, refType=null, unstructuredReference=Harris D. 2023. Single-pilot airline operations: designing the aircraft may be the easy part. The Aeronautical Journal,127(1313): 1171-1191 [DOI: 10.1017/aer.2022.110], articleTitle=Single-pilot airline operations: designing the aircraft may be the easy part, refAbstract=null), Reference(id=1322961428319187416, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=null, rfOrder=31, authorNames=He K M, Zhang X Y, Ren S Q, Sun J, journalName=null, refType=null, unstructuredReference=He K M,Zhang X Y,Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90], articleTitle=Deep residual learning for image recognition, refAbstract=null), Reference(id=1322961428369519065, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=null, pageStart=73113, pageEnd=73140, url=null, language=null, rfNumber=null, rfOrder=32, authorNames=Hoenig A, Roy K, Acquaah Y T, Yi S, Desai S S, journalName=IEEE Access, refType=null, unstructuredReference=Hoenig A,Roy K,Acquaah Y T,Yi S and Desai S S. 2024. Explainable AI for cyber-physical systems: issues and challenges. IEEE Access,12: 73113-73140 [DOI: 10.1109/ACCESS.2024.3395444], articleTitle=Explainable AI for cyber-physical systems: issues and challenges, refAbstract=null), Reference(id=1322961428449210842, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=Hörhager P, journalName=null, refType=null, unstructuredReference=Hörhager P. 2025. Aircraft Automation and Human Performance: An Analysis of Flight Deck Failures. Wien,Austria: Technische Universität Wien [DOI: 10.34726/hss.2025.84080], articleTitle=Aircraft Automation and Human Performance: An Analysis of Flight Deck Failures. Wien,Austria: Technische Universität Wien, refAbstract=null), Reference(id=1322961428507931099, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=65, issue=1, pageStart=2, pageEnd=12, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=Husain A M, journalName=The Neurodiagnostic Journal, refType=null, unstructuredReference=Husain A M. 2025. Of pilots and copilots: the evolving role of artificial intelligence in clinical neurophysiology. The Neurodiagnostic Journal,65(1): 2-12 [DOI: 10.1080/21646821.2025.2465089], articleTitle=Of pilots and copilots: the evolving role of artificial intelligence in clinical neurophysiology, refAbstract=null), Reference(id=1322961428570845660, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=5, issue=2, pageStart=null, pageEnd=42, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=Kirwan B, journalName=Future Transportation, refType=null, unstructuredReference=Kirwan B. 2025. Human factors requirements for human-AI teaming in aviation. Future Transportation,5(2): #42 [DOI: 10.3390/futuretransp5020042], articleTitle=Human factors requirements for human-AI teaming in aviation, refAbstract=null), Reference(id=1322961428646343133, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=4, pageStart=null, pageEnd=7, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=Korentsides M S J, Keebler J R, Fausett C M, Patel S M, Lazzara E H, journalName=Journal of Aviation/Aerospace Education and Research, refType=null, unstructuredReference=Korentsides M S J,Keebler J R,Fausett C M,Patel S M and Lazzara E H. 2024. Human-AI teams in aviation: considerations from human factors and team science. Journal of Aviation/Aerospace Education and Research,33(4): #7 [DOI: 10.58940/2329-258X.2046], articleTitle=Human-AI teams in aviation: considerations from human factors and team science, refAbstract=null), Reference(id=1322961428726034910, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=16, pageEnd=40, url=null, language=null, rfNumber=null, rfOrder=37, authorNames=Koul P, journalName=Advances in Mechanical and Materials Engineering, refType=null, unstructuredReference=Koul P. 2025. A review of machine learning applications in aviation engineering. Advances in Mechanical and Materials Engineering,42(1): 16-40 [DOI: 10.7862/rm.2025.2], articleTitle=A review of machine learning applications in aviation engineering, refAbstract=null), Reference(id=1322961428801532383, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=21, issue=11, pageStart=1515, pageEnd=1522, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Kuang W T, Mao K C, Huang J C, Li H B, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Kuang W T,Mao K C,Huang J C and Li H B. 2016. Fatigue driving detection based on sclera Gaussian model. Journal of Image and Graphics,21(11): 1515-1522, articleTitle=Fatigue driving detection based on sclera Gaussian model, refAbstract=null), Reference(id=1322961428864446944, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=21, issue=11, pageStart=1515, pageEnd=1522, url=null, language=null, rfNumber=null, rfOrder=39, authorNames=旷文腾, 毛宽诚, 黄家才, 李海彬, journalName=中国图象图形学报, refType=null, unstructuredReference=旷文腾,毛宽诚,黄家才,李海彬. 2016. 基于高斯眼白模型的疲劳驾驶检测. 中国图象图形学报,21(11): 1515-1522 [DOI: 10.11834/jig.20161111], articleTitle=基于高斯眼白模型的疲劳驾驶检测, refAbstract=null), Reference(id=1322961430114349538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2004, volume=46, issue=1, pageStart=50, pageEnd=80, url=null, language=null, rfNumber=null, rfOrder=40, authorNames=Lee J D, See K A, journalName=Human Factors: The Journal of the Human Factors and Ergonomics Society, refType=null, unstructuredReference=Lee J D and See K A. 2004. Trust in automation: designing for appropriate reliance. Human Factors: The Journal of the Human Factors and Ergonomics Society,46(1): 50-80 [DOI: 10.1518/hfes.46.1.50_30392], articleTitle=Trust in automation: designing for appropriate reliance, refAbstract=null), Reference(id=1322961430202429923, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=7, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=null, rfOrder=41, authorNames=Lei H J, Yao C K, journalName=Navigation Positioning and Timing, refType=null, unstructuredReference=Lei H J and Yao C K. 2020. Technical architecture of aviation artificial intelligence for military application. Navigation Positioning and Timing,7(1): 1-11, articleTitle=Technical architecture of aviation artificial intelligence for military application, refAbstract=null), Reference(id=1322961430273733092, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=7, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=null, rfOrder=42, authorNames=雷宏杰, 姚呈康, journalName=导航定位与授时, refType=null, unstructuredReference=雷宏杰,姚呈康. 2020. 面向军事应用的航空人工智能技术架构研究. 导航定位与授时,7(1): 1-11 [DOI: 10.19306/j.cnki.2095-8110.2020.01.001], articleTitle=面向军事应用的航空人工智能技术架构研究, refAbstract=null), Reference(id=1322961430345036261, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=43, authorNames=Lillicrap T P, Hunt J J, Pritzel A, Heess N, Erez T, Tassa Y, journalName=null, refType=null, unstructuredReference=Lillicrap T P,Hunt J J,Pritzel A,Heess N,Erez T,Tassa Y,et al. 2016. Continuous control with deep reinforcement learning//Proceedings of the 4th International Conference on Learning Representations. San Juan,Puerto Rico,USA: ICLR [DOI: 10.48550/arXiv.1509.02971], articleTitle=Continuous control with deep reinforcement learning, refAbstract=null), Reference(id=1322961430403756518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2017, volume=32, issue=7, pageStart=4, pageEnd=21, url=null, language=null, rfNumber=null, rfOrder=44, authorNames=Lim Y, Bassien-Capsa V, Ramasamy S, Liu J, Sabatini R, journalName=IEEE Aerospace and Electronic Systems Magazine, refType=null, unstructuredReference=Lim Y,Bassien-Capsa V,Ramasamy S,Liu J and Sabatini R. 2017. Commercial airline single-pilot operations: system design and pathways to certification. IEEE Aerospace and Electronic Systems Magazine,32(7): 4-21 [DOI: 10.1109/MAES.2017.160175], articleTitle=Commercial airline single-pilot operations: system design and pathways to certification, refAbstract=null), Reference(id=1322961430483448295, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=8, issue=3, pageStart=null, pageEnd=65, url=null, language=null, rfNumber=null, rfOrder=45, authorNames=Lin Y, journalName=Aerospace, refType=null, unstructuredReference=Lin Y. 2021. Spoken instruction understanding in air traffic control: challenge,technique,and application. Aerospace,8(3): #65 [DOI: 10.3390/aerospace8030065], articleTitle=Spoken instruction understanding in air traffic control: challenge,technique,and application, refAbstract=null), Reference(id=1322961430554751464, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=#525150, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=46, authorNames=Lu X L, Du Z L, Xu Y, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=Lu X L,Du Z L and Xu Y. 2021. Review on basic concept and applications for artificial intelligence in aviation. Acta Aeronautica et Astronautica Sinica,42(4): #525150, articleTitle=Review on basic concept and applications for artificial intelligence in aviation, refAbstract=null), Reference(id=1322961430621860329, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=null, pageEnd=525150, url=null, language=null, rfNumber=null, rfOrder=47, authorNames=卢新来, 杜子亮, 许赟, journalName=航空学报, refType=null, unstructuredReference=卢新来,杜子亮,许赟. 2021. 航空人工智能概念与应用发展综述. 航空学报,42(4): #525150 [DOI: 10.7527/S1000-6893.2021.25150], articleTitle=航空人工智能概念与应用发展综述, refAbstract=null), Reference(id=1322961430697357802, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=null, pageStart=21, pageEnd=39, url=null, language=null, rfNumber=null, rfOrder=48, authorNames=Memon M, Narejo S, Talpur S, Channa A, Mangi F A, Pandey J K, journalName=Machine Learning based Air Traffic Surveillance System Using Image Processing, refType=null, unstructuredReference=Memon M,Narejo S,Talpur S,Channa A,Mangi F A and Pandey J K. 2026. Explainable AI (XAI) in air traffic monitoring systems//Pandey J K,Rai M,Ahmad F,eds. Machine Learning based Air Traffic Surveillance System Using Image Processing. Bingley: Emerald Publishing Limited: 21-39 [DOI: 10.1108/978-1-80592-062-520251002], articleTitle=Explainable AI (XAI) in air traffic monitoring systems, refAbstract=null), Reference(id=1322961430768660971, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2015, volume=518, issue=7540, pageStart=529, pageEnd=533, url=null, language=null, rfNumber=null, rfOrder=49, authorNames=Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, journalName=Nature, refType=null, unstructuredReference=Mnih V,Kavukcuoglu K,Silver D,Rusu A A,Veness J,Bellemare M G,et al. 2015. Human-level control through deep reinforcement learning. Nature,518(7540): 529-533 [DOI: 10.1038/nature14236], articleTitle=Human-level control through deep reinforcement learning, refAbstract=null), Reference(id=1322961430831575532, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=null, rfOrder=50, authorNames=Niermann C, Ebrecht L, Küls J, Findeisen M S, Hofmann T, journalName=null, refType=null, unstructuredReference=Niermann C,Ebrecht L,Küls J,Findeisen M S and Hofmann T. 2023. Development process for a remote co-pilot to support single-pilot operation in a next-generation air transportation system//Proceedings of the 14th International Conference on Applied Human Factors and Ergonomics and the Affiliated. San Francisco,USA: AHFE International: 1-11 [DOI: 10.54941/ahfe1003914], articleTitle=Development process for a remote co-pilot to support single-pilot operation in a next-generation air transportation system, refAbstract=null), Reference(id=1322961430886101485, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=6, pageStart=52, pageEnd=56, url=null, language=null, rfNumber=null, rfOrder=51, authorNames=Pei Y, He L, journalName=Aeronautic Standardization and Quality, refType=null, unstructuredReference=Pei Y and He L. 2025. Research on the construction technology of high-quality datasets for aviation standard quality large models. Aeronautic Standardization and Quality,(6): 52-56, articleTitle=Research on the construction technology of high-quality datasets for aviation standard quality large models, refAbstract=null), Reference(id=1322961430949016046, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=6, pageStart=52, pageEnd=56, url=null, language=null, rfNumber=null, rfOrder=52, authorNames=裴育, 何柳, journalName=航空标准化与质量, refType=null, unstructuredReference=裴育,何柳. 2025. 基于航空标准质量大模型数据集高质量构建实践. 航空标准化与质量,(6): 52-56 [DOI: 10.13237/j.cnki.asq.2025.06.11], articleTitle=基于航空标准质量大模型数据集高质量构建实践, refAbstract=null), Reference(id=1322961431007736303, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=null, rfOrder=53, authorNames=Redmon J, Divvala S, Girshick R, Farhadi A, journalName=null, refType=null, unstructuredReference=Redmon J,Divvala S,Girshick R and Farhadi A. 2016. You only look once: unified,real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA: IEEE: 779-788 [DOI: 10.1109/CVPR.2016.91], articleTitle=You only look once: unified,real-time object detection, refAbstract=null), Reference(id=1322961431087428080, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/1707.06347.pdf, language=null, rfNumber=null, rfOrder=54, authorNames=Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O, journalName=null, refType=null, unstructuredReference=Schulman J,Wolski F,Dhariwal P,Radford A and Klimov O. 2017. Proximal policy optimization algorithms [EB/OL]. [2026-04-14]., articleTitle=Proximal policy optimization algorithms, refAbstract=null), Reference(id=1322961431141954033, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=9, pageStart=2616, pageEnd=2643, url=null, language=null, rfNumber=null, rfOrder=55, authorNames=Shi Z H, Wu C W, Li C J, You Z Z, Wang Q, Ma C C, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Shi Z H,Wu C W,Li C J,You Z Z,Wang Q and Ma C C. 2023. Object detection techniques based on deep learning for aerial remote sensing images: a survey. Journal of Image and Graphics,28(9): 2616-2643, articleTitle=Object detection techniques based on deep learning for aerial remote sensing images: a survey, refAbstract=null), Reference(id=1322961431267783154, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=9, pageStart=2616, pageEnd=2643, url=null, language=null, rfNumber=null, rfOrder=56, authorNames=石争浩, 仵晨伟, 李成建, 尤珍臻, 王泉, 马城城, journalName=中国图象图形学报, refType=null, unstructuredReference=石争浩,仵晨伟,李成建,尤珍臻,王泉,马城城. 2023. 航空遥感图像深度学习目标检测技术研究进展. 中国图象图形学报,28(9): 2616-2643 [DOI: 10.11834/jig.221085], articleTitle=航空遥感图像深度学习目标检测技术研究进展, refAbstract=null), Reference(id=1322961431334892019, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=null, rfOrder=57, authorNames=Sridhar B, journalName=null, refType=null, unstructuredReference=Sridhar B. 2020. Applications of machine learning techniques to aviation operations: promises and challenges//Proceedings of 2020 International Conference on Artificial Intelligence and Data Analytics for Air Transportation. Singapore,Singapore: IEEE: 1-12 [DOI: 10.1109/AIDA-AT48540.2020.9049205], articleTitle=Applications of machine learning techniques to aviation operations: promises and challenges, refAbstract=null), Reference(id=1322961431414583796, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2006, volume=49, issue=12/13, pageStart=1288, pageEnd=1311, url=null, language=null, rfNumber=null, rfOrder=58, authorNames=Stanton N A, Stewart R, Harris D, Houghton R J, Baber C, McMaster R, journalName=Ergonomics, refType=null, unstructuredReference=Stanton N A,Stewart R,Harris D,Houghton R J,Baber C,McMaster R,et al. 2006. Distributed situation awareness in dynamic systems: theoretical development and application of an ergonomics methodology. Ergonomics,49(12/13): 1288-1311 [DOI: 10.1080/00140130600612762], articleTitle=Distributed situation awareness in dynamic systems: theoretical development and application of an ergonomics methodology, refAbstract=null), Reference(id=1322961431674630645, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=27, issue=3, pageStart=177, pageEnd=186, url=null, language=null, rfNumber=null, rfOrder=59, authorNames=Sui D, Ma C Y, Dong J T, journalName=Aviation, refType=null, unstructuredReference=Sui D,Ma C Y and Dong J T. 2023. Conflict resolution strategy based on deep reinforcement learning for air traffic management. Aviation,27(3): 177-186 [DOI: 10.3846/aviation.2023.19720], articleTitle=Conflict resolution strategy based on deep reinforcement learning for air traffic management, refAbstract=null), Reference(id=1322961431754322423, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=null, rfOrder=60, authorNames=Sutthithatip S, Perinpanayagam S, Aslam S, Wileman A, journalName=null, refType=null, unstructuredReference=Sutthithatip S,Perinpanayagam S,Aslam S and Wileman A. 2021. Explainable AI in aerospace for enhanced system performance//Proceedings of the 40th IEEE/AIAA Digital Avionics Systems Conference. San Antonio,USA: IEEE: 1-7 [DOI: 10.1109/DASC52595.2021.9594488], articleTitle=Explainable AI in aerospace for enhanced system performance, refAbstract=null), Reference(id=1322961431817236984, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=61, authorNames=Sutton R S, Barto A G, journalName=null, refType=null, unstructuredReference=Sutton R S and Barto A G. 2018. Reinforcement Learning: An Introduction. 2nd ed. Cambridge,USA: The MIT Press, articleTitle=Reinforcement Learning: An Introduction. 2nd ed. Cambridge,USA: The MIT Press, refAbstract=null), Reference(id=1322961431888540153, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=null, rfOrder=62, authorNames=Szymanski M, Ghazi G, Botez R M, journalName=null, refType=null, unstructuredReference=Szymanski M,Ghazi G and Botez R M. 2023. Single and multi-agent reinforcement learning approach to optimize aircraft ground trajectories at airports//Proceedings of 2023 Aerospace Europe Conference. Lausanne: EUCASS: 1-14 [DOI: 10.13009/EUCASS2023-713], articleTitle=Single and multi-agent reinforcement learning approach to optimize aircraft ground trajectories at airports, refAbstract=null), Reference(id=1322961432177947130, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=6, pageStart=1956, pageEnd=1987, url=null, language=null, rfNumber=null, rfOrder=63, authorNames=Tao J H, Wu Y C, Yu C, Weng D D, Li G J, Han T, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Tao J H,Wu Y C,Yu C,Weng D D,Li G J,Han T,et al. 2022. A survey on multi-modal human-computer interaction. Journal of Image and Graphics,27(6): 1956-1987, articleTitle=A survey on multi-modal human-computer interaction, refAbstract=null), Reference(id=1322961432245055995, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=null, volume=27, issue=6, pageStart=1956, pageEnd=1987, url=null, language=null, rfNumber=null, rfOrder=64, authorNames=陶建华, 巫英才, 喻纯, 翁冬冬, 李冠君, 韩腾, journalName=多模态人机交互综述. 中国图象图形学报, refType=null, unstructuredReference=陶建华,巫英才,喻纯,翁冬冬,李冠君,韩腾,等. 2022. 多模态人机交互综述. 中国图象图形学报,27(6): 1956-1987 [DOI: 10.11834/jig.220151], articleTitle=2022, refAbstract=null), Reference(id=1322961432534462972, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=4, pageStart=142, pageEnd=152, url=null, language=null, rfNumber=null, rfOrder=65, authorNames=Tokadlı G, Dorneich M C and Matessa M, journalName=Journal of Air Transportation, refType=null, unstructuredReference=Tokadlı G,Dorneich M C and Matessa M. 2021. Toward human-autonomy teaming in single-pilot operations: domain analysis and requirements. Journal of Air Transportation,29(4): 142-152 [DOI: 10.2514/1.D0240], articleTitle=Toward human-autonomy teaming in single-pilot operations: domain analysis and requirements, refAbstract=null), Reference(id=1322961432614154749, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=538, issue=null, pageStart=null, pageEnd=114194, url=null, language=null, rfNumber=null, rfOrder=66, authorNames=Tonti F, Rabault J, Vinuesa R, journalName=Journal of Computational Physics, refType=null, unstructuredReference=Tonti F,Rabault J and Vinuesa R. 2025. Navigation in a simplified urban flow through deep reinforcement learning. Journal of Computational Physics,538: #114194 [DOI: 10.1016/j.jcp.2025.114194], articleTitle=Navigation in a simplified urban flow through deep reinforcement learning, refAbstract=null), Reference(id=1322961432689652223, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=6000, pageEnd=6010, url=null, language=null, rfNumber=null, rfOrder=67, authorNames=Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, journalName=null, refType=null, unstructuredReference=Vaswani A,Shazeer N,Parmar N,Uszkoreit J,Jones L,Gomez A N,et al. 2017. Attention is all you need//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach,USA: Curran Associates Inc.: 6000-6010, articleTitle=Attention is all you need, refAbstract=null), Reference(id=1322961432970670592, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=1, pageStart=null, pageEnd=20518, url=null, language=null, rfNumber=null, rfOrder=68, authorNames=Wang Y S, Guo X Y, Guo S S, Jiang F, Liang Z P, Peng L, journalName=Scientific Reports, refType=null, unstructuredReference=Wang Y S,Guo X Y,Guo S S,Jiang F,Liang Z P,Peng L,et al. 2025. Machine learning evaluation model of pilot workload in a low-visibility environment. Scientific Reports,15(1): #20518 [DOI: 10.1038/s41598-025-05759-7], articleTitle=Machine learning evaluation model of pilot workload in a low-visibility environment, refAbstract=null), Reference(id=1322961433062945282, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=6, pageStart=null, pageEnd=294, url=null, language=null, rfNumber=null, rfOrder=69, authorNames=Wang Z, Pan W J, Li H, Wang X, Zuo Q H, journalName=Aerospace, refType=null, unstructuredReference=Wang Z,Pan W J,Li H,Wang X and Zuo Q H. 2022. Review of deep reinforcement learning approaches for conflict resolution in air traffic control. Aerospace,9(6): #294 [DOI: 10.3390/aerospace9060294], articleTitle=Review of deep reinforcement learning approaches for conflict resolution in air traffic control, refAbstract=null), Reference(id=1322961433125859843, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=297, pageEnd=315, url=null, language=null, rfNumber=null, rfOrder=70, authorNames=Würfel J, Papenfuß A and Wies M, journalName=Operationalizing AI explainability using interpretability cues in the cockpit: insights from user-centered development of the intelligent pilot advisory system (IPAS)//Proceedings of the 5th International Conference on Artificial Intelligence in HCI,AI-HCI 2024,held as part of the 26th International Conference, refType=null, unstructuredReference=Würfel J,Papenfuß A and Wies M. 2024. Operationalizing AI explainability using interpretability cues in the cockpit: insights from user-centered development of the intelligent pilot advisory system (IPAS)//Proceedings of the 5th International Conference on Artificial Intelligence in HCI,AI-HCI 2024,held as part of the 26th International Conference. Washington,USA: Springer: 297-315 [DOI: 10.1007/978-3-031-60606-9_17], articleTitle=null, refAbstract=null), Reference(id=1322961433197163012, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2018, volume=19, issue=3, pageStart=353, pageEnd=374, url=null, language=null, rfNumber=null, rfOrder=71, authorNames=Wynne K T, Lyons J B, journalName=Theoretical Issues in Ergonomics Science, refType=null, unstructuredReference=Wynne K T and Lyons J B. 2018. An integrative model of autonomous agent teammate-likeness. Theoretical Issues in Ergonomics Science,19(3): 353-374 [DOI: 10.1080/1463922X.2016.1260181], articleTitle=An integrative model of autonomous agent teammate-likeness, refAbstract=null), Reference(id=1322961433264271877, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=41, pageEnd=44, url=null, language=null, rfNumber=null, rfOrder=72, authorNames=Xu X F, Gao Y J, Liu Z, journalName=null, refType=null, unstructuredReference=Xu X F,Gao Y J and Liu Z. 2020. Research on the application of artificial intelligence technology in flight test//Proceedings of the 17th China Aviation Measurement and Control Technology Annual Conference. Xi’an: National Defense Technology Industry Automation Testing Innovation Center: 41-44, articleTitle=Research on the application of artificial intelligence technology in flight test, refAbstract=null), Reference(id=1322961433331380742, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=41, pageEnd=44, url=null, language=null, rfNumber=null, rfOrder=73, authorNames=徐小芳, 高雅娟, 刘钊, journalName=第十七届中国航空测控技术年会论文集, refType=null, unstructuredReference=徐小芳,高雅娟,刘钊. 2020. 人工智能技术在飞行试验中的应用研究//第十七届中国航空测控技术年会论文集. 西安: 国防科技工业自动化测试创新中心: 41-44 [DOI: 10.26914/c.cnkihy.2020.027547], articleTitle=人工智能技术在飞行试验中的应用研究, refAbstract=null), Reference(id=1322961433432044039, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2026, volume=71, issue=null, pageStart=null, pageEnd=104378, url=null, language=null, rfNumber=null, rfOrder=74, authorNames=Yiu C Y, Li W C, Ng K K H, Chi C F, Schiefele J, journalName=Advanced Engineering Informatics, refType=null, unstructuredReference=Yiu C Y,Li W C,Ng K K H,Chi C F and Schiefele J. 2026. Enhancing aviation safety with artificial intelligence: a systematic literature review on recent advances,challenges and future perspectives. Advanced Engineering Informatics,71: #104378 [DOI: 10.1016/j.aei.2026.104378], articleTitle=Enhancing aviation safety with artificial intelligence: a systematic literature review on recent advances,challenges and future perspectives, refAbstract=null), Reference(id=1322961433490764296, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=6, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=null, rfOrder=75, authorNames=Zhang J, Zeng R, journalName=null, refType=null, unstructuredReference=Zhang J and Zeng R. 2020. Mode design and test for commercial aircraft single-pilot operations. Aeronautical Science and Technology,31(6): 42-49, articleTitle=Mode design and test for commercial aircraft single-pilot operations, refAbstract=null), Reference(id=1322961433566261769, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=6, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=null, rfOrder=76, authorNames=张炯, 曾锐, journalName=航空科学技术, refType=null, unstructuredReference=张炯,曾锐. 2020. 商用飞机单一飞行员驾驶模式设计及测试. 航空科学技术,31(6): 42-49 [DOI: 10.19452/j.issn1007-5453.2020.06.007], articleTitle=商用飞机单一飞行员驾驶模式设计及测试, refAbstract=null), Reference(id=1322961435243983372, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2023, volume=2, issue=4, pageStart=null, pageEnd=100107, url=null, language=null, rfNumber=null, rfOrder=77, authorNames=Zhang M C, Yan C, Dai W, Xiang X J, Low K H, journalName=Green Energy and Intelligent Transportation, refType=null, unstructuredReference=Zhang M C,Yan C,Dai W,Xiang X J and Low K H. 2023. Tactical conflict resolution in urban airspace for unmanned aerial vehicles operations using attention-based deep reinforcement learning. Green Energy and Intelligent Transportation,2(4): #100107 [DOI: 10.1016/j.geits.2023.100107], articleTitle=Tactical conflict resolution in urban airspace for unmanned aerial vehicles operations using attention-based deep reinforcement learning, refAbstract=null), Reference(id=1322961435344646669, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=9, issue=3, pageStart=92, pageEnd=96, url=null, language=null, rfNumber=null, rfOrder=78, authorNames=Zheng X Q, Shi W L, journalName=Journal of Civil Aviation, refType=null, unstructuredReference=Zheng X Q and Shi W L. 2025. An aviation speech recognition system software based on artificial intelligence and its application. Journal of Civil Aviation,9(3): 92-96, articleTitle=An aviation speech recognition system software based on artificial intelligence and its application, refAbstract=null), Reference(id=1322961435462087182, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025, volume=9, issue=3, pageStart=92, pageEnd=96, url=null, language=null, rfNumber=null, rfOrder=79, authorNames=郑晓庆, 史万里, journalName=民航学报, refType=null, unstructuredReference=郑晓庆,史万里. 2025. 一种基于人工智能的航空语音识别系统软件及应用. 民航学报,9(3): 92-96 [DOI: 10.3969/j.issn.2096-4994.2025.03.018], articleTitle=一种基于人工智能的航空语音识别系统软件及应用, refAbstract=null), Reference(id=1322961435541778959, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=325109, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=80, authorNames=Zhou B, Guo Y, Li N, Zhong X J, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=Zhou B,Guo Y,Li N and Zhong X J. 2021. Path planning of UAV using guided enhancement Q-learning algorithm. Acta Aeronautica et Astronautica Sinica,42(9): 325109, articleTitle=Path planning of UAV using guided enhancement Q-learning algorithm, refAbstract=null), Reference(id=1322961435604693520, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=null, pageEnd=325109, url=null, language=null, rfNumber=null, rfOrder=81, authorNames=周彬, 郭艳, 李宁, 钟锡健, journalName=航空学报, refType=null, unstructuredReference=周彬,郭艳,李宁,钟锡健. 2021. 基于导向强化Q学习的无人机路径规划. 航空学报,42(9): #325109 [DOI: 10.7527/S1000-6893.2021.25109], articleTitle=基于导向强化Q学习的无人机路径规划, refAbstract=null), Reference(id=1322961435684385297, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025a, volume=7, issue=1, pageStart=249, pageEnd=262, url=null, language=null, rfNumber=null, rfOrder=82, authorNames=Ziakkas D, Henneberry D, Plioutsias A, journalName=Human-Intelligent Systems Integration, refType=null, unstructuredReference=Ziakkas D,Henneberry D and Plioutsias A. 2025a. Designing human-centric intelligent systems in aviation: applications of artificial cognitive systems,AI-enhanced investigations,and immersive eVTOL simulation training. Human-Intelligent Systems Integration,7(1): 249-262 [DOI: 10.1007/s42454-025-00083-x], articleTitle=Designing human-centric intelligent systems in aviation: applications of artificial cognitive systems,AI-enhanced investigations,and immersive eVTOL simulation training, refAbstract=null), Reference(id=1322961435751494162, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2025b, volume=88, issue=null, pageStart=305, pageEnd=314, url=null, language=null, rfNumber=null, rfOrder=83, authorNames=Ziakkas D, Pechlivanis K, Plioutsias A, journalName=Transportation Research Procedia, refType=null, unstructuredReference=Ziakkas D,Pechlivanis K and Plioutsias A. 2025b. Enhancing aviation risk assessment through artificial intelligence: the single pilot operations case study. Transportation Research Procedia,88: 305-314 [DOI: 10.1016/j.trpro.2025.05.037], articleTitle=Enhancing aviation risk assessment through artificial intelligence: the single pilot operations case study, refAbstract=null), Reference(id=1322961435881517587, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=2297, pageEnd=2301, url=null, language=null, rfNumber=null, rfOrder=84, authorNames=Zuluaga-Gomez J, Motlicek P, Zhan Q R, Veselý K, Braun R, journalName=null, refType=null, unstructuredReference=Zuluaga-Gomez J,Motlicek P,Zhan Q R,Veselý K and Braun R. 2020. Automatic speech recognition benchmark for air-traffic communications//Proceedings of the 21st Annual Conference of the International Speech Communication Association. Shanghai,China: ISCA: 2297-2301 [DOI: 10.21437/Interspeech.2020-2173], articleTitle=Automatic speech recognition benchmark for air-traffic communications, refAbstract=null), Reference(id=1322961436087038484, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, doi=null, pmid=null, pmcid=null, year=2024, volume=2, issue=5, pageStart=1, pageEnd=45, url=null, language=null, rfNumber=null, rfOrder=85, authorNames=Zuluaga-Gomez J, Veselý K, Szöke I, Blatt A, Motlicek P, Kocour M, journalName=Journal of Data-Centric Machine Learning Research, refType=null, unstructuredReference=Zuluaga-Gomez J,Veselý K,Szöke I,Blatt A,Motlicek P,Kocour M,et al. 2024. ATCO2 corpus: a large-scale dataset for research on automatic speech recognition and natural language understanding of air traffic control communications. Journal of Data-Centric Machine Learning Research,2(5): 1-45, articleTitle=ATCO2 corpus: a large-scale dataset for research on automatic speech recognition and natural language understanding of air traffic control communications, refAbstract=null)], funds=[Fund(id=1322961423919362486, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, awardId=null, language=EN, fundingSource=National Natural Science Foundation of China (62376217,62576279,62301434);Young Elite Scientists Sponsorship Program by CAST(2023QNRC001), fundOrder=null, country=null), Fund(id=1322961423986471351, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, awardId=null, language=CN, fundingSource=国家自然科学基金项目(62376217,62576279,62301434);中国科协青年人才托举工程项目(2023QNRC001), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322961418890391929, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=1, ext=[AuthorCompanyExt(id=1322961418898780538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961418911363451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学计算机学院,西安 710129)]), AuthorCompany(id=1322961418970083708, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=2, ext=[AuthorCompanyExt(id=1322961418978472317, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China), AuthorCompanyExt(id=1322961418991055230, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 沈阳飞机设计研究所,沈阳 110035)]), AuthorCompany(id=1322961419066552703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=3, ext=[AuthorCompanyExt(id=1322961419074941312, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China), AuthorCompanyExt(id=1322961419083329921, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西北工业大学卓越工程师学院,西安 710072)]), AuthorCompany(id=1322961419142050178, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=4, ext=[AuthorCompanyExt(id=1322961419150438787, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China), AuthorCompanyExt(id=1322961419158827396, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 清华大学航天航空学院,北京 100084)]), AuthorCompany(id=1322961419230130565, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=5, ext=[AuthorCompanyExt(id=1322961419242713478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961419251102087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学电子信息学院,西安 710129)])], figs=[ArticleFig(id=1322961422925312428, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, label=Fig.1, caption=Overall architecture of AI-assisted single-pilot operation system, figureFileSmall=JNfz22pHaeIxEiLLQ/Ko7Q==, figureFileBig=jKT8HUxKPrM6xxWCCdv4lg==, tableContent=null), ArticleFig(id=1322961423017587117, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, label=图1, caption=融合人工智能的单机长驾驶系统整体架构, figureFileSmall=JNfz22pHaeIxEiLLQ/Ko7Q==, figureFileBig=jKT8HUxKPrM6xxWCCdv4lg==, tableContent=null), ArticleFig(id=1322961423252468142, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, label=Fig.2, caption=Multimodal pilot state monitoring technology framework, figureFileSmall=kPOx0Z1TVTDtSOCnRDsT2Q==, figureFileBig=u+OQZzVwz86msxvWL7xsZw==, tableContent=null), ArticleFig(id=1322961423327965615, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, label=图2, caption=多模态感知驱动的飞行员状态监测技术体系, figureFileSmall=kPOx0Z1TVTDtSOCnRDsT2Q==, figureFileBig=u+OQZzVwz86msxvWL7xsZw==, tableContent=null), ArticleFig(id=1322961423411851696, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, label=Fig.3, caption=Comparison of airworthiness certification paradigms between traditional aviation software and AI systems, figureFileSmall=PHlLBpelx+6tQ+XvAJYG/g==, figureFileBig=Z/D44nmXYHEuDRErrxNGxw==, tableContent=null), ArticleFig(id=1322961423495737777, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, label=图3, caption=传统航空软件与AI认证范式对比, figureFileSmall=PHlLBpelx+6tQ+XvAJYG/g==, figureFileBig=Z/D44nmXYHEuDRErrxNGxw==, tableContent=null), ArticleFig(id=1322961423567040946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, label=Fig.4, caption=Four-layer XAI technical pathway framework for SPO airworthiness compliance, figureFileSmall=AXZ3+6MQXEnBx3q/pFO7iw==, figureFileBig=l3KXjfZtUPO/u+/i+Zpgfw==, tableContent=null), ArticleFig(id=1322961423638344115, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, label=图4, caption=面向SPO适航的可解释AI四层技术路径框架, figureFileSmall=AXZ3+6MQXEnBx3q/pFO7iw==, figureFileBig=l3KXjfZtUPO/u+/i+Zpgfw==, tableContent=null), ArticleFig(id=1322961423722230196, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=EN, label=Table 1, caption=Comparison of mainstream deep reinforcement learning algorithms for single-pilot operations, figureFileSmall=null, figureFileBig=null, tableContent=
算法类型动作空间稳定性
PPOOn-policy连续/离散高
SACOff-policy连续高
DDPGOff-policy连续中等
TD3Off-policy连续高
DQNOff-policy离散中等
MARLMulti-agent连续/离散低
), ArticleFig(id=1322961423801921973, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, language=CN, label=表1, caption=

面向单机长运行的主流深度强化学习算法对比

, figureFileSmall=null, figureFileBig=null, tableContent=
算法类型动作空间稳定性
PPOOn-policy连续/离散高
SACOff-policy连续高
DDPGOff-policy连续中等
TD3Off-policy连续高
DQNOff-policy离散中等
MARLMulti-agent连续/离散低
)], attaches=null, journal=Journal(id=1249023527618129992, delFlag=0, nameCn=中国图象图形学报, nameEn=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, issn=1006-8961, eissn=null, cn=11-3758, coden=CODEN ZTTXFZ, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=uirXtX858YS3zEpFXZttJA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Image and Graphics, journalRemark=null, publicationField=null, createdTime=1775720014721, updatedTime=1788951488513, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=uirXtX858YS3zEpFXZttJA==, picEn=bud7qaxfvWHeFsbyBTAiKQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304520351199814396, language=CN, name=中国图象图形学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488542, updatedTime=1788951488542, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304520351250146045, language=EN, name=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488554, updatedTime=1788951488554, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1249024232475115590, websiteList=[Website(id=1249025782459334881, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN, language=CN, createTime=1775720552315, createBy=18614031015, updateTime=1775720586268, updateBy=18614031015, name=中国图象图形学报-中文, tplId=1146099689490845704, title=中国图象图形学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026166254928133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=articleTextType, value=kx, createTime=1775720643819, updateTime=1775720643819, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166221373698, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=banner, value=null, createTime=1775720643811, updateTime=1775720643811, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166271705352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=grayFlag, value=0, createTime=1775720643823, updateTime=1775720643823, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166212985089, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720643809, updateTime=1775720643809, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166288482570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=minRunFlag, value=0, createTime=1775720643827, updateTime=1775720643827, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166246539524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic, createTime=1775720643817, updateTime=1775720643817, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166280093961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=silenceFlag, value=0, createTime=1775720643825, updateTime=1775720643825, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166233956611, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1775720643814, updateTime=1775720643814, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166259122438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeColor, value=null, createTime=1775720643820, updateTime=1775720643820, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166267511047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeStyle, value=null, createTime=1775720643822, updateTime=1775720643822, creator=18614031015, updator=18614031015)]), Website(id=1249025782681633001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN, language=EN, createTime=1775720552368, createBy=18614031015, updateTime=1775720607118, updateBy=18614031015, name=中国图象图形学报-英文, tplId=1146101810881728533, title=Journal of Image and Graphics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026195371786511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=articleTextType, value=kx, createTime=1775720650761, updateTime=1775720650761, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195355009292, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=banner, value=null, createTime=1775720650757, updateTime=1775720650757, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195392758034, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=grayFlag, value=0, createTime=1775720650766, updateTime=1775720650766, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195342426379, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720650754, updateTime=1775720650754, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195409535252, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=minRunFlag, value=0, createTime=1775720650770, updateTime=1775720650770, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195367592206, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic, createTime=1775720650760, updateTime=1775720650760, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195401146643, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=silenceFlag, value=0, createTime=1775720650768, updateTime=1775720650768, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195359203597, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1775720650758, updateTime=1775720650758, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195380175120, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeColor, value=null, createTime=1775720650763, updateTime=1775720650763, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195388563729, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeStyle, value=null, createTime=1775720650765, updateTime=1775720650765, creator=18614031015, updator=18614031015)])], journalTitle=中国图象图形学报, weixinUrl=null, journalUrl=https://www.cjig.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Image and Graphics, journalPhotoCn=uirXtX858YS3zEpFXZttJA==, journalPhotoEn=bud7qaxfvWHeFsbyBTAiKQ==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.260216, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.260216, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.260216, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.260216, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1789488000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
人工智能辅助的单机长飞行驾驶技术综述
收藏切换
PDF下载
袁林 1 , 李阳 2, 3 , 苗延飞 4 , 李枭扬 5 , 曹聪琦 1, *
中国图象图形学报 | 大模型在航空领域的智慧赋能 2026,31(9): 3227-3250
收起
收藏切换
中国图象图形学报 |大模型在航空领域的智慧赋能 2026 , 31 (9) : 3227 -3250
人工智能辅助的单机长飞行驾驶技术综述
全屏
[Author(id=1322961419326599561, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lin.y@mail.nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419406291339, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419326599561, language=EN, stringName=Lin Yuan, firstName=Lin, middleName=null, lastName=Yuan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419477594508, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419326599561, language=CN, stringName=袁林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西北工业大学计算机学院,西安 710129, bio={"content":"

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

"}, bioImg=null, bioContent=

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418890391929, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=1, ext=[AuthorCompanyExt(id=1322961418898780538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961418911363451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学计算机学院,西安 710129)])]), Author(id=1322961419553091982, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tianciyang2010@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419636978065, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419553091982, language=EN, stringName=Yang Li, firstName=Yang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China
3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419704086930, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419553091982, language=CN, stringName=李阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 沈阳飞机设计研究所,沈阳 110035
3 西北工业大学卓越工程师学院,西安 710072, bio={"content":"

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

"}, bioImg=null, bioContent=

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418970083708, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=2, ext=[AuthorCompanyExt(id=1322961418978472317, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China), AuthorCompanyExt(id=1322961418991055230, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418970083708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 沈阳飞机设计研究所,沈阳 110035)]), AuthorCompany(id=1322961419066552703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=3, ext=[AuthorCompanyExt(id=1322961419074941312, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China), AuthorCompanyExt(id=1322961419083329921, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419066552703, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西北工业大学卓越工程师学院,西安 710072)])]), Author(id=1322961419779584404, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=miaoyf20@mails.tsinghua.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961419871859094, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419779584404, language=EN, stringName=Yanfei Miao, firstName=Yanfei, middleName=null, lastName=Miao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961419938967959, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961419779584404, language=CN, stringName=苗延飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 清华大学航天航空学院,北京 100084, bio={"content":"

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

"}, bioImg=null, bioContent=

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961419142050178, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=4, ext=[AuthorCompanyExt(id=1322961419150438787, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China), AuthorCompanyExt(id=1322961419158827396, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419142050178, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 清华大学航天航空学院,北京 100084)])]), Author(id=1322961420006076825, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lixiaoyang@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961421675409819, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961420006076825, language=EN, stringName=Xiaoyang Li, firstName=Xiaoyang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961421755101596, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961420006076825, language=CN, stringName=李枭扬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 西北工业大学电子信息学院,西安 710129, bio={"content":"

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

"}, bioImg=null, bioContent=

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961419230130565, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=5, ext=[AuthorCompanyExt(id=1322961419242713478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961419251102087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961419230130565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学电子信息学院,西安 710129)])]), Author(id=1322961421855764894, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=congqi.cao@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961421935456672, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961421855764894, language=EN, stringName=Congqi Cao, firstName=Congqi, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961422027731361, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, authorId=1322961421855764894, language=CN, stringName=曹聪琦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 西北工业大学计算机学院,西安 710129, bio={"content":"

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

"}, bioImg=null, bioContent=

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961418890391929, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, xref=1, ext=[AuthorCompanyExt(id=1322961418898780538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China), AuthorCompanyExt(id=1322961418911363451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961414566064491, companyId=1322961418890391929, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学计算机学院,西安 710129)])])]
袁林1 , 李阳2, 3 , 苗延飞4 , 李枭扬5 , 曹聪琦1, *
作者信息
  • 1 西北工业大学计算机学院,西安 710129
  • 2 沈阳飞机设计研究所,沈阳 110035
  • 3 西北工业大学卓越工程师学院,西安 710072
  • 4 清华大学航天航空学院,北京 100084
  • 5 西北工业大学电子信息学院,西安 710129
通讯作者:
作者简介:

袁林,男,博士研究生,主要研究方向为计算机视觉和大模型视觉理解。E-mail:

李阳,男,高级工程师,主要研究方向为体系对抗、空战战术战法设计和控制工程。E-mail:

苗延飞,男,高级工程师,主要研究方向为体系试验。E-mail:

李枭扬,男,副研究员,主要研究方向为智能决策、传感器管理和指挥控制。E-mail:

曹聪琦,通信作者,女,副教授,主要研究方向为计算机视觉、智能视频理解、数据高效学习与时空预测。E-mail:

Artificial intelligence-assisted flight technologies for single-pilot operations: a comprehensive review
Lin Yuan1 , Yang Li2, 3 , Yanfei Miao4 , Xiaoyang Li5 , Congqi Cao1, *
Affiliations
  • 1 School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China
  • 2 Shenyang Aircraft Design and Research Institute,Shenyang 110035,China
  • 3 National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an 710072,China
  • 4 School of Aerospace Engineering,Tsinghua University,Beijing 100084,China
  • 5 School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China
出版时间: 2026-09-16 doi: 10.11834/jig.260216
文章导航
收藏切换

随着全球航空运输需求持续增长,单机长体制(single-pilot operation,SPO)成为民航领域应对飞行员短缺与人力成本攀升的核心发展方向。然而,从双人机组向单人驾驶的转变,核心瓶颈在于如何填补缺失副驾驶后产生的认知与决策空缺。“AI(artificial intelligence)副驾驶”概念的提出,旨在通过具备深度感知、语义理解与自主决策能力的智能系统,与人类飞行员构建认知型协作关系。本文系统梳理了人工智能辅助飞行驾驶的关键技术,构建了“感知—认知—推理—交互决策—安全监控”的系统分析框架。重点阐述了基于脑电图(electroencephalogram,EEG)、功能性近红外光谱(functional near-infrared spectroscopy,fNIRS)以及计算机视觉的多模态生理行为感知技术,分析了其在实时监测飞行员负荷与疲劳状态方面的最新进展。同时,针对复杂的陆空通话环境,探讨了基于大模型架构的空管指令意图识别与语义提取技术。此外,本文还归纳了大模型与深度强化学习协同驱动的智能航路规划与冲突解算方法,并深入剖析了当前阻碍AI技术商业化落地的核心壁垒,包括深度学习模型的不可解释性、人机信任机制的缺失以及非确定性智能系统的适航认证困境。最后,本文指出大模型驱动的多模态统一架构与运行时保障适航路径是未来航空人工智能发展的关键方向,旨在为实现高透明度、深层人机协同的智能驾驶舱提供参考。

人工智能(AI)  /  AI副驾驶  /  飞行员状态感知  /  智能语音交互  /  深度强化学习(DRL)

Today,the aviation industry faces a critical shortage of qualified pilots and escalating labor costs due to the continuous surge in global air transport demand. Consequently,single-pilot operation (SPO) has emerged as a strategic evolution in civil aviation to optimize crew resources and mitigate pilot fatigue,especially during long-haul flights. However,the transition from traditional multicrew cockpits to a single-pilot environment is not merely a reduction in personnel; rather,it introduces a significant “cognitive and decision-making gap” previously filled by the co-pilot. To bridge this gap,this paper proposes the concept of the “AI co-pilot” —— an intelligent system designed to establish a deep cognitive collaborative relationship with the human pilot through advanced perception,semantic understanding,and autonomous decision-making capabilities. This paper provides a systematic and comprehensive review of the core technological components enabling AI-assisted piloting. In this work,we propose a four-layer analytical framework known as “perception-cognition-interaction-decision-safety monitoring”. This structure serves as a blueprint for integrating heterogeneous AI modules into the high-integrity environment of an aircraft cockpit. First,we look into multimodal physiological and behavioral sensing technologies that are essential for the real-time monitoring of a pilot’s workload and fatigue state. Given that traditional subjective assessments are insufficient for high-dynamic flight environments,this review focuses on the integration of electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS). In particular,we provide a critical analysis of their trade-offs: while EEG offers superior temporal resolution capable of capturing instantaneous cognitive shifts,fNIRS demonstrates stronger robustness against motion artifacts in a vibrating cockpit. Furthermore,computer vision (CV) techniques are discussed for the nonintrusive monitoring of facial expressions,percentage of eyelid closure (PERCLOS),and visual tunneling effects. The fusion of these modalities allows the AI Co-pilot to “read” the pilot’s state and trigger adaptive automation upon detection of cognitive overload. Second,the review explores intelligent speech interaction and semantic understanding within the complex controller-pilot data link communications (CPDLC) and radio environments. The aviation context poses unique challenges,including low signal-to-noise ratios in VHF communications and nonstandard accents. In this paper,we analyze the application of LLMs and transformer-based architectures in intent recognition and slot filling for air traffic control (ATC) instructions. By parsing complex,nested instructions into executable parameters,the AI Co-pilot functions as an “intelligent radio operator” that significantly reduces the auditory and manual workload of the single pilot. Third,we summarize intelligent route planning and dynamic conflict resolution driven by the synergy of large models and deep reinforcement learning (DRL). Algorithms such as proximal policy optimization (PPO) and soft actor-critic (SAC) are evaluated for their efficacy in continuous action spaces and high-dimensional flight dynamics. Unlike traditional rule-based flight management systems (FMS),AI-driven planners can explore optimal trajectories in unconstrained airspace and respond adaptively to extreme weather or system failures. Additionally,we emphasize the transition from individual agent optimization to multiagent reinforcement learning (MARL) for collaborative collision avoidance in dense urban air mobility (UAM) scenarios. A significant portion of this review is dedicated to the core barriers that hinder the commercial deployment of aviation AI. We provide an in-depth analysis of the non-interpretability of “black-box” deep learning models,which prevents human pilots from establishing calibrated trust during time-critical emergencies. Furthermore,the paradigm conflict between the nondeterministic nature of AI and traditional deterministic airworthiness standards (e.g.,DO-178C) is dissected. We also discuss the latest policy trends from EASA and the FAA,highlighting the shift toward “run-time assurance (RTA)” frameworks. Specifically,RTA acts as a safety shield,bounding the outputs of complex AI models within a predefined safe flight envelope and ultimately providing a viable certification pathway. Finally,this paper presents a perspective on future trends. We posit that the next generation of aviation AI will evolve toward a “multimodal unified architecture” in which text,speech,vision,and flight dynamics are aligned in a single latent space. We predict that this evolution will transform the AI Co-pilot from a collection of isolated subtasks into a holistic “cognitive partner”. By emphasizing transparency,bidirectional communication,and standardized certification,this review aims to provide a theoretical foundation and engineering reference for achieving high-transparency,deep human-machine collaborative intelligent cockpits in the SPO era.

artificial intelligence (AI)  /  AI co-pilot  /  pilot state awareness  /  intelligent speech interaction  /  deep reinforcement learning
袁林, 李阳, 苗延飞, 李枭扬, 曹聪琦. 人工智能辅助的单机长飞行驾驶技术综述. 中国图象图形学报, 2026 , 31 (9) : 3227 -3250 . DOI: 10.11834/jig.260216
Lin Yuan, Yang Li, Yanfei Miao, Xiaoyang Li, Congqi Cao. Artificial intelligence-assisted flight technologies for single-pilot operations: a comprehensive review[J]. Journal of Image and Graphics, 2026 , 31 (9) : 3227 -3250 . DOI: 10.11834/jig.260216
自莱特兄弟发明飞机以来,航空技术的每一次飞跃都伴随着自动化水平的提升。随着全球航空运输需求的持续增长,传统依赖双人机组(机长与副驾驶)的商业飞行模式正面临人力成本攀升、飞行员短缺以及长途飞行导致的严重疲劳等严峻挑战。为应对这些挑战,航空业开始探索利用先进的人工智能(artificial intelligence,AI)技术来辅助甚至替代部分人类飞行员的职能。事实上,将智能系统引入驾驶舱的构想由来已久,早在20世纪90年代,研究人员就提出了“飞行员助手”(pilot’s associate)这一基于知识的协作系统概念。近年来,人工智能正经历从传统判别式小模型向生成式多模态大模型(generative multimodal foundation models)的范式跃迁。这一颠覆性突破使得航空AI系统首次具备了跨模态的统一表征与常识推理能力,从而为彻底填补单机长模式下的“智能空缺”,实现人机深度协同展现出了前所未有的跨越式发展潜力,如图1所示。
在此技术演进的背景下,单机长体制(single-pilot operation,SPO)逐渐成为国际民航组织、学术界及各大航空制造企业关注的核心焦点。SPO的最终目标是通过高度自动化的智能系统,使商用客机能够由单一人类飞行员安全、高效地完成从起飞到降落的全过程飞行任务。然而,单人驾驶绝非简单地从驾驶舱中移除一名副驾驶,这意味着剩下的唯一人类机长将承受成倍增加的物理与认知负荷。一旦遭遇极端恶劣天气、系统严重故障或复杂的空中交通管制等突发紧急情况,单名飞行员极易陷入情境意识丧失和决策超载的险境。因此,真正决定SPO能否成功落地的关键挑战在于:系统设计必须能够完美弥补缺失副驾驶后带来的“智能空缺”,使得未来的航空控制系统拥有超越以往的强大态势感知和高级逻辑推理能力。
为了彻底填补这一智能空缺,“AI副驾驶”的概念应运而生,并迅速成为近年来的前沿研究热点。传统的自动驾驶仪(autopilot)主要依赖预设的固定控制律执行确定性任务,缺乏对复杂、未知动态环境的自适应能力。AI副驾驶被定位为一个具备深度感知、语义理解、自主决策与自然交互能力的“认知型虚拟队友”,不仅能够通过多传感器融合实时监测飞机的物理飞行状态与飞行员的生理心理负荷,还能协助处理繁杂的通信联络、动态航路规划以及早期故障排查等高强度脑力任务。特别是随着自然语言处理技术和生成式大模型的引入,基于大语言模型架构的AI副驾驶开始能够以自然、流畅的语言与机长进行双向沟通,极大地重塑了传统的驾驶舱人机交互模式与操作隐喻。
尽管人工智能辅助驾驶技术展现出广阔的前景,但其从实验室环境走向实际商业部署仍面临诸多棘手的学术与工程壁垒。首先,当前基于深度神经网络的黑盒模型缺乏足够的透明度与可解释性,导致人类飞行员在生死攸关的关键时刻难以建立对AI自主决策的绝对信任。其次,现有的文献研究多局限于特定的独立子任务(如单一的语音识别或孤立的局部避障),系统架构严重缺乏对驾驶舱内人机深度协同与控制权动态分配的系统性整合。最后,航空业历来以极其严苛的系统级安全标准著称,如何为具备数据驱动、自学习特征的非确定性智能系统制定一套切实可行的适航认证标准,也是当前阻碍其规模化应用的硬性瓶颈。
针对上述国际最新研究进展及现存的技术局限,本文旨在对人工智能辅助飞行员驾驶技术进行系统、全面的综述。本文将依次梳理单机长体制的演进架构、基于多模态感知的飞行员状态监测技术、面向空管的智能语音语义交互模型,以及基于深度强化学习的智能航路规划算法,并在此基础上,深入剖析可解释性人工智能(explainable artificial intelligence,XAI)与适航认证所面临的核心挑战,以期为该领域的未来研究方向提供系统性的梳理与前瞻性参考。
单机长体制(SPO)的演进并非单一技术的突进,而是航空系统工程、人因学理论与人工智能技术深度交融的产物。为实现从传统双人机组向单人驾驶的平稳过渡,学术界与工业界对驾驶舱自动化的底层逻辑进行了彻底重构。本节将从自动化范式的演进、天地协同操作模式的互补性,以及核心技术架构的系统化设计3个维度,对当前AI辅助驾驶的理论基础与工程架构进行系统综述。
在探讨人工智能如何重塑驾驶舱之前,必须深刻理解传统航空自动化所面临的理论瓶颈。自20世纪七、八十年代飞行管理系统(flight management system,FMS)和高级自动驾驶仪大规模引入商用客机以来,航空业确立了“以人为中心的飞行器自动化”这一核心指导原则(Billings,1991)。在这一传统范式下,自动化系统被严格定义为人类飞行员的“高级工具”或“辅助设备”。这种系统按照确定性的控制律(如PID(proportional-integral-derivative)控制)运行,其核心特征是“被动执行”:系统仅在人类预设的指令边界内精确工作,既不具备对外部复杂环境的自主语义理解能力,也无法推断人类机长的潜在意图。尽管这种辅助型自动化极大地降低了巡航阶段的体力和基本的操纵负荷,但在面对非标准程序或多重突发故障时,系统往往会因为超出预设包线而迅速断开,将控制权生硬地交还给飞行员。实证研究表明,传统驾驶舱自动化系统的这种刚性失效是导致多起典型飞行事故的深层诱因(Hörhager,2025)。因此,评估机器学习(machine learning,ML)技术在航空运营中的应用前景与底层鲁棒性挑战,成为新一代系统变革的重要课题(Sridhar,2020)。
随着全球航空运输密度的激增,将单机长体制(SPO)推向商业应用成为缓解飞行员短缺和降低运营成本的重要路径(Lim等,2017)。然而,单人驾驶的引入彻底打破了传统双人机组中的“交叉检查”(cross-check)与“任务分担”(task-sharing)机制。研究表明,在SPO架构下,单名人类机长在面对诸如恶劣天气突变、多重系统失效或高密度终端区调度等极端边缘场景时,其认知与生理负荷将呈现指数级增长(Harris,2007,2023)。在这种高压状态下,传统辅助型自动化工具的局限性被无限放大。当人类机长陷入“认知隧道”(cognitive tunneling)或发生注意狭窄时,缺乏自主感知能力的传统工具不仅无法提供有效的决策支持,反而可能因为频繁的告警信息进一步加剧情境意识(situation awareness,SA)的丧失(Endsley,2017a)。从人机协同的宏观视角来看,SPO模式的成功极大地依赖于人在回路与控制体之间“分布式情境意识”的连续构筑与互补维持(Stanton等,2006)。
为了彻底解决单人驾驶带来的安全隐患,航空人机交互的底层哲学开始从“人机交互”(human- computer interaction,HCI)向“人机协同”(human- autonomy teaming,HAT)发生深刻的范式转移。这一概念的雏形可追溯至20世纪90年代美国国防高级研究计划局发起的“飞行员助手”(Pilot’s Associate)项目,该项目首次尝试构建一个基于知识库的协作系统,旨在为战机飞行员提供战术建议(Banks和Lizza,1991)。虽然受限于当时的计算算力与数据规模未能全面普及,但其为现代AI副驾驶奠定了理论先声。
在现代人机协同(HAT)理论框架下,人工智能不再是冷冰冰的执行工具,而是赋予了与人类副驾驶类似特质的“虚拟队友”(Chen和Barnes,2014)。一个合格的AI队友必须具备3个核心特征:意图共享(shared intent)、双向沟通(bidirectional communication)以及动态信任调节(dynamic trust calibration)(Wynne和Lyons,2018)。这意味着未来的驾驶舱自动化系统必须能够持续追踪飞机的飞行轨迹与机长的生理负荷,主动预测下一个可能的操作步骤,并在机长出现遗漏或失误时,以符合人类认知习惯的方式进行平滑干预(Tokadlı等,2021)。这种从被动“辅助”到主动“协同”的范式转移,构成了新一代单机长飞机座舱设计的基石,也从根本上决定了必须引入具备深度学习与推理能力的人工智能大模型,以弥补传统专家系统的智能空缺。
在确立了人机协同的理论范式后,如何在地空物理空间中合理部署这一“AI副驾驶”,成为实现单机长体制的关键工程挑战。目前,学术界与工业界普遍认为,单一的机载智能系统或纯粹的地面远程控制均存在固有的安全脆弱性。因此,构建一个融合“机载AI助理”(airborne AI assistant)与“地面远程副驾驶”(remote co-pilot,RCP)的空地一体化协同架构,被视为走向商业化SPO的最优解与必由之路。
首先,地面远程副驾驶(RCP)概念为单机长提供了强大的战略支援与系统冗余。RCP系统通常部署在航空公司总部的多机控制中心,由经验丰富的人类飞行员结合高级自动化系统共同运作(Niermann等,2023)。在常规的巡航阶段,一名RCP可以同时监控多架SPO客机的遥测数据,充当“超级签派员”的角色;而当某一特定航班遭遇恶劣天气、复杂故障或进入高密度的进近着陆阶段时,RCP可以将注意力集中于该单一航班,通过高带宽的地空数据链与机载系统握手,实质性地承担起传统右座副驾驶的职责,提供实时的战术建议甚至直接接管部分非关键飞行控制权。RCP架构的最大优势在于其能够充分利用地面无限的计算资源、全局的空管气象大数据,以及人类专家在处理“未知之未知”(unknown unknowns)时的创造性思维,这是目前任何单体AI都无法匹敌的。
然而,RCP架构高度依赖于地空通信链路的稳定性和极低的延迟。一旦遭遇严重的电磁干扰、网络攻击或身处大洋/极地上空的通信盲区,导致数据链丢失(loss of communication,LOC),高空中的单名飞行员将瞬间陷入孤立无援的绝境。正是在这一致命的物理隔离痛点下,机载AI助理展现出不可替代的互补价值。机载AI助理被物理固化在飞机的航电设备中,具备完全自主的本地算力和独立的传感器输入通道(Arteaga,2024)。在常规运行中,机载AI助理主要扮演“认知减负者”的角色,承担诸如电子检查单(electronic checklist,ECL)自动朗读与核对、无线电通信频率自动调谐以及飞行管理系统(FMS)参数预填等烦琐的程序性任务(Davidoff等,2024)。
随着自然语言处理(natural language processing,NLP)和生成式预训练大模型(large language model,LLM)的爆发,基于对话机器人架构的机载AI助理在航空领域的应用潜力被深度挖掘。从产业经济学与工程应用的角度看,AI副驾驶的引入不仅能够优化机组资源,更被视为航空公司应对市场剧烈波动、确立长远可持续竞争优势的核心技术引擎(Dzreke,2025;Koul,2025)。研究指出,这种基于自然语言交互的AI副驾驶能够通过语音交互快速响应飞行员的非结构化查询(如“检索当前液压系统失效的最新处置程序”),极大地缩短了机组在紧急情况下的信息检索时间与视觉扫视负荷(Durach和Gutierrez,2024)。当天地数据链断开时,机载AI助理能够无缝接管由于RCP缺位而留下的安全空白,通过机载雷达与视觉传感器的融合进行自主避障与航路重规划。综上所述,机载AI助理提供了微秒级的战术响应与绝对的断网冗余,而RCP则提供了全局的战略视野与人类伦理兜底,两者在空间分布与功能层级的深度互补,共同编织了SPO模式下坚不可摧的冗余安全网。
在人工智能辅助单机长驾驶领域,国内外研究重点呈现出一定的差异性与互补性。欧美航空机构(如NASA(National Aeronautics and Space Administration)、EASA(European Union Aviation Safety Agency))起步较早,侧重于顶层人机协同概念框架的构建与大规模多智能体空域的虚拟仿真,其在机组人因工程中的AI前沿应用已有系统的研究梳理(Flores等,2024)。相比之下,近年来国内民航机构、主机所及顶尖高校在SPO与AI副驾驶的工程化落地方面取得了显著的本土突破。例如,国内主机所结合国产大机型的研制与预研需求,重点攻关基于多模态大模型的机载智能系统架构设计(卢新来 等,2021;雷宏杰和姚呈康,2020);国内高校与科研机构则针对中国高密度空域的特殊运行环境,在带有浓重地方口音的中文陆空通话意图理解(郑晓庆和史万里,2025)等特定任务上实现了技术领跑,为AI副驾驶的区域化应用提供了坚实的底层算法支撑。
无论是机载的认知助手还是地面的智能分发系统,其实际效能都取决于底层技术架构的健壮性。构建一个符合航空高安全等级标准(如DO-178C)的人工智能辅助驾驶系统,绝不仅是单一深度学习算法的移植,而是一项横跨多学科的复杂系统工程(卢新来 等,2021)。当前主流的航空人工智能技术架构通常设计为松耦合的层级化结构,以确保非确定性AI模型与确定性传统航电系统的安全物理隔离(雷宏杰和姚呈康,2020),其核心技术栈主要可划分为感知层、认知推理层、交互决策层以及安全监控层。
第1层为多模态智能感知层(perception layer)。在SPO环境下,态势感知的范围从传统的“机外环境”延伸至“机内人员状态”。该层汇聚了海量的异构数据流,一方面,它实时接入飞机自身的物理传感网络(如皮托管、惯导系统、气象雷达)以获取飞行器的精确6自由度动力学状态;另一方面,它通过部署在驾驶舱内的红外眼动仪、脑电采集阵列(electroencephalogram ,EEG)等设备,不间断地采集飞行员的生理与行为学特征(Debie等,2021)。在此阶段,高性能的边缘计算硬件用于执行数据清洗、时空同步与多传感器特征级融合,将高维、嘈杂的原始电信号和视觉信号转化为低维、高价值的特征向量,为后续的推理提供高质量的输入源。
第2层为深度认知与推理层(cognition & reasoning layer)。这是AI副驾驶的“大脑中枢”,广泛应用了机器学习与深度神经网络技术(Ahmed,2025)。在该层中,各种针对特定航空任务微调的专业大模型被并行激活。例如,自然语言理解(natural language understanding,NLU)模块实时解析空管的嘈杂无线电指令;计算机视觉网络对跑道障碍物、潜在危险气象或关键航空目标进行深度学习特征提取与高精度定位(石争浩 等,2023);同时,认知负荷评估模型则根据感知层提供的神经生理数据,对当前机长是否处于疲劳、分心或信息超载状态进行量化评级(Yiu等,2026)。在此架构设计中,各推理模块往往采用集成学习策略,通过多个异构小模型的交叉验证来降低单一深度网络“灾难性遗忘”或局部最优带来的系统性风险。在传统的松耦合架构中,各推理模块往往采用独立的异构小模型;而新一代架构正加速向“统一的航空多模态大模型底座”迈进。该基座大模型充当AI副驾驶的大脑中枢,能够在一个统一的潜在空间(latent space)内,直接对齐多源生理序列、视觉特征与空管文本,从根本上消解了子系统间的逻辑割裂与信息孤岛问题。
第3层为交互与规划决策层(interaction and decision layer)。该层负责将推理层的抽象理解转化为具体的操作建议与人机协同动作。针对复杂空管与飞行环境,深度强化学习算法被大量应用于生成具有前瞻性的四维(3D空间 + 时间)避撞轨迹和最优进近航路。更重要的是,该层搭载了高度复杂的动态控制权分配逻辑。系统会基于当前环境的紧急程度与飞行员的认知状态指数,决定是仅通过语音/平视显示器(head-up display,HUD)提供柔性建议(Badrinath和Balakrishnan,2022),还是在判断飞行员失能的极端情况下,直接向自动飞行指引系统(automatic flight guidance system,AFDS)发送硬性控制指令以接管飞机。
第4层为不可或缺的安全监控与屏障层(safety and monitor layer)。由于深度学习本质上是数据驱动的黑盒模型,存在不可预见的非确定性输出风险,为了满足航空业对灾难性失效条件每飞行小时失效概率极低的严苛要求(10-9),系统架构中必须引入运行时保障(run-time assurance,RTA)机制(Degas等,2022)。安全监控层充当了一个绝对可靠的、基于确定性物理法则与逻辑规则构建的“包线保护器”。所有来自AI层的决策指令,在下发至飞控计算机(flight control computer,FCC)之前,都必须穿过这一过滤层。一旦监控器检测到AI生成的指令试图将飞机带入失速、超速等危险状态,监控层将立刻否决该指令,并将系统降级至传统的安全备用模式。这种“复杂但不确定”的AI与“简单但绝对可靠”的规则监控器的异构集成架构,是目前推动AI技术走向实际飞行验证的核心工程范式。在我国国产机型的试飞工业实践中,针对飞行试验高风险场景的人工智能技术探索也在同步推进,为高风险科目的试飞安全闭环提供了重要的辅助验证手段(徐小芳 等,2020)。
在单机长体制(SPO)的安全架构下,AI副驾驶不仅仅需要掌握对飞行器物理层面的精准控制,更核心且更具挑战性的任务是实现对座舱内唯一的“人类机长”进行不间断的实时状态监控与认知对齐。在传统的双人机组中,机长与副驾驶之间通过语言交流、眼神接触以及对彼此操作的交叉检查共同维持态势感知并防范人为失误。然而在单人驾驶模式下,由于失去了人类副驾驶的物理监督,AI系统必须主动承担起“监控者”的角色,具备精准判断机长是否处于疲劳、分心、信息超载(information overload)或生理失能等高风险状态的能力。这种状态感知的结果,是触发AI副驾驶介入干预或进行动态控制权无缝分配(dynamic function allocation)的根本依据。传统的飞行员心智负荷评估主要依赖于诸如NASA-TLX量表的主观问卷,这种方式存在严重的滞后性和主观偏误,完全无法满足现代高动态飞行环境对实时性的严苛要求。近年来,随着穿戴式传感器的微型化以及深度学习算法的突飞猛进,基于客观生理指标与外部行为特征的多模态实时状态监测技术取得了革命性进展。本节将从神经生理信号提取、计算机视觉行为分析以及多源异构数据融合3个核心维度,系统综述多模态感知驱动的飞行员状态监测前沿技术及理论验证,整体技术架构如图2所示。
心智负荷(mental workload,MWL)是指飞行员在特定时间段内处理飞行任务所消耗的认知资源总量。当任务需求超过飞行员的处理极限时,会导致注意力崩溃、反应迟缓以及关键安全信息的遗漏。在诸多客观评估手段中,神经生理学信号因其直接反映大脑皮层活动的特质,被公认为评估认知状态的“黄金标准”。目前,脑电图(EEG)和功能性近红外光谱(functional near-infrared spectroscopy ,fNIRS)是航空人因工程领域应用最为广泛的两种前沿技术,而人工智能与临床神经生理信号解析的交叉融合,也正在深度重塑智能控制实体的行为理解边界(Husain,2025)。
脑电图(EEG)通过放置在飞行员头皮表面的电极阵列,以极高的时间分辨率(通常在毫秒级)捕捉大脑神经元集群放电产生的微弱电位变化。这种高频(high frequency,HF)动态特性使得EEG能够异常敏锐地捕捉到飞行员在执行复杂任务(如突发故障排查、恶劣天气进近)时瞬间的认知负荷激增或应激反应。然而,传统的EEG信号处理方法在航空应用中面临着巨大的挑战。飞行座舱是一个充满了机械震动、电磁干扰以及高频噪音的恶劣物理环境,这导致采集到的EEG原始信号中常常夹杂着大量由眼电(electrooculogram,EOG)、肌电(electromyography,EMG)以及外界设备引起的伪影(artifacts)。为了从这些高维、非平稳的噪信中提取有效的特征,研究人员开始引入先进的深度网络拓扑结构。STGCN(spatio-temporal graph convolutional network)模型不仅能够提取单一电极随时间变化的动态特征,还能捕捉不同大脑区域之间的空间拓扑相关性,从而在模拟飞行任务中成功实现了高精度的脑力负荷分类。
尽管深度学习极大地提升了EEG的可用性,但其穿戴准备过程较为烦琐,且对头部运动依然极为敏感。作为互补,功能性近红外光谱技术(fNIRS)近年来在神经科学及临床应用中取得了长足进步,并被迅速引入航空航天领域(Chen等,2020)。fNIRS的工作原理是利用近红外光穿透颅骨,通过测量大脑前额叶皮层(主要负责高级认知、执行控制和决策)中氧合血红蛋白(oxyHb)和脱氧血红蛋白(deoxyHb)的浓度变化,以间接反映神经激活程度。与EEG相比,fNIRS虽然在时间分辨率上略逊一筹(血液动力学响应通常有几秒的延迟),但其对飞行员轻微的头部晃动、身体震动表现出极高的鲁棒性,更加适合在高度动态的真实飞行器座舱中部署。Gateau等人(2018)在一项具有里程碑意义的研究中,首次证明了基于fNIRS的被动脑机接口(passive brain computer interface,passive BCI)能够在真实的云上飞行(over the clouds)环境中,对轻型飞机飞行员的心智状态进行精准的实时评估。这一突破不仅跨越了从实验室模拟器到真实物理飞行的鸿沟,也为预防由“认知隧道效应”导致的飞行事故提供了全新的技术闭环。在近期的研究中,学者们进一步将可解释的机器学习和深度残差收缩网络(deep residual shrinkage network)应用于fNIRS数据的脑功能连接分析,在处理模拟多重发动机失效等紧急迫降场景时,能够以极高的准确率对飞行员的认知超载进行分级预警。这种技术演进意味着,未来的AI副驾驶可以直接“读取”机长大脑的工作状态,在机长认知崩溃前提前接管低优先级的飞行任务。
在实际航空应用中,EEG与fNIRS存在显著的适用场景差异与优劣势权衡。EEG具备毫秒级的高时间分辨率,能够敏锐捕捉飞行员瞬间的认知失误与应激反应,但其极易受到座舱电磁干扰与飞行员肌肉运动(EMG)伪影的影响;相比之下,fNIRS对头部运动和电气噪声具有极强的鲁棒性,更适合座舱等自然移动环境。然而,fNIRS测量的是大脑血液动力学响应,存在5~7 s的固有时间延迟,这使得它难以捕捉极速的突发性操作事件,而更适用于评估长航时飞行中持续性的心智负荷状态。
虽然基于EEG和fNIRS的神经生理监测技术提供了极高的数据保真度,但不可忽视的是,这些设备通常需要贴附在飞行员的皮肤上或要求佩戴特殊的头套。在长达数小时乃至十几个小时的跨洲际越洋商业飞行中,这种侵入性(intrusive)的穿戴要求会引发显著的物理不适和热应激,从而在实际商业化部署中遇到极大的阻力。因此,基于计算机视觉(computer vision,CV)的非接触式行为监测技术,凭借其无感化、隐蔽性好以及易于与现有座舱监控摄像头集成的优势,成为另一条核心的研究主线。
视觉监测技术主要聚焦于对面部表情、头部姿态以及眼动轨迹的持续捕获与模式识别。在疲劳与注意力涣散检测方面,基于计算机视觉的方法已被证实能够有效提取眼部和面部的关键行为特征以客观判别监控对象的疲劳状态(旷文腾 等,2016)。研究进一步发现在航空应用中,飞行员的面部运动特征(如眨眼频率的增加、闭眼时间的延长、打哈欠的频次)与生理疲劳状态呈现高度的正相关。Chen等人(2019)开发了一种基于深度学习的实时面部表情与头部姿态分析算法,最初用于连续监控高强度作业下的空中交通管制员的工作负荷变化。该研究指出,通过卷积神经网络(convolutional neural network,CNN)提取面部关键点特征,可以精准计算出“闭眼时间占比”(percentage of eyelid closure,PERCLOS)等公认的疲劳生理指标,该技术架构已开始直接迁移至SPO驾驶舱内。现代AI模型(如长短期记忆网络(long short-term memory,LSTM)或双向门控循环单元(bidirectional gate recurrent unit,Bi-GRU))能够将这些面部的空间视觉特征与时间序列动态结合,进一步区分飞行员是在正常交谈还是处于微睡眠(microsleep)的前兆状态。
除了疲劳检测,注意力资源的分配与情境意识(SA)的维持对于SPO同样生死攸关。眼动追踪(eye-tracking)是视觉行为分析中的关键环节,通过安装在仪表板或平视显示器(HUD)边缘的高清红外摄像头,AI副驾驶能够实时获取飞行员的瞳孔直径、注视点(fixation)、扫视轨迹(saccade)以及驻留时间。在复杂的飞行环境(如仪表气象条件下的盲降)中,飞行员必须在主飞行显示器(primary flight display,PFD)、导航显示器(navigation display,ND)和发动机指示系统之间进行合理且规律的视觉扫描。当飞行员面临极度紧张或认知过载时,往往会出现“视觉隧道效应”(visual tunneling),即视线专注于某单一仪表而忽略了周边其他灾难性的告警信息。目前,基于注意力机制的特征提取网络以及诸如ResNet(residual network)(He等,2016)和YOLO(you only look once)(Redmon等,2016)等成熟的深度残差与目标检测架构,已应用于在光线剧烈变化(如强烈的阳光直射或夜航)的座舱环境中稳定提取眼动参数。为了攻克这种因极端光学退化导致的视觉解算瓶颈,引入物理先验或物理约束的智能计算机视觉架构成为当前提升跨场景鲁棒性的重要演进方向(Banerjee等,2025)。通过混合神经网络(如引入Bi-FPN(bidirectional feature pyramid network)模块进行多尺度特征融合),AI系统可以在极低的延迟下(例如62 ms级别)对眼球视线矢量进行三维重建,从而准确评估飞行员在当前观察—判断—决策—执行(observe-orient-decide-act,OODA)循环中的视觉注意力是否分配得当,确保关键的飞行仪表未被长时间忽略。
尽管单一模态的感知技术在各自领域均取得了显著进展,但无论哪种单一技术都存在其固有的物理瓶颈与场景局限。例如,神经生理设备(EEG)容易受到肌肉运动伪影的严重干扰;而基于计算机视觉的非接触感知技术,则在飞行员佩戴墨镜、氧气面罩,或是座舱处于极端光照条件(如逆光、全黑)时,面临严重的特征丢失与性能降级。因此,为了在SPO架构下构建一个具备航空级可靠性(满足DO-178C高安全保证等级)的状态监控系统,向多模态信息融合(multimodal information fusion)与多模态人机交互演进成为学术界与工业界的必然共识(陶建华 等,2022)。Debie等人(2021)在对认知负荷客观评估的系统性回顾中明确指出,采用多源异构传感器融合的网络架构,在鲁棒性和分类精度上显著优于任何单一模态模型。实证研究进一步表明,仅使用眼动特征或单一脑电信号的分类准确率通常在40%~96%之间波动,而将眼动、脑电以及其他生理特征进行深度融合的多模态方法,能够在极度复杂的任务中实现高达98%的预测准确率。
在更宏观的“人—机—环”航空闭环系统考量中,飞行员的状态并非孤立存在,而是与飞机实时的飞行动力学(flight dynamics)以及外部气象环境高度耦合。一个成熟的多源异构感知模型,不仅需要融合飞行员自身的“内生状态”(如心率变异性(heart rate variability,HRV)、皮电反应(electrodermal skin response,EDS)、瞳孔扩张和脑部氧合),更需要将其与来自飞行数据记录器(flight data recorder,FDR)的“外生状态”(如飞机的当前高度、俯仰角、地速、下降率)进行时空同步与联合分析。例如,在自动驾驶仪稳定巡航阶段,较低的心率和较少的眼球扫视可能代表状态良好;但如果此时飞机正处于低能见度进近(low-visibility approach)、存在严重侧风或突发发动机喘振的边缘环境,同样的低生理唤醒状态则极可能意味着飞行员已经陷入了致命的失能。Wang等人(2025)针对这一挑战,提出了一种将飞机控制状态参量与人类生理行为数据进行多模态异构融合的机器学习评估模型,专门用于构建更加鲁棒的低能见度环境飞行员负荷基准。依托多模态大模型(multimodal large language model,MLLM)强大的跨域对齐与涌现能力,最新的研究不再依赖烦琐的传统人工特征提取,而是将飞机的海量时序动力学参数与飞行员的眼动视频流、脑电序列直接送入统一的大模型架构中。大模型凭借其海量的预训练先验知识,能够敏锐捕捉机舱环境骤变与人类微弱生理应激之间的深层隐含语义,成功预测飞行员在复杂进近中的情境意识层级。
此外,从系统应用的角度来看,多模态融合感知的终极目的在于“防患于未然”。Alreshidi等人(2024)的系统性综述强调,推进基于机器学习的心理生理大数据分析,不仅能够客观把控机长当下的工作状态,更能在此基础上建立起闭环反馈(closed-loop feedback)机制以实质性地推进航空安全。一旦多模态融合引擎推断出当前人类机长的综合评估得分跌破安全阈值,AI副驾驶系统将根据策略引擎进行接管:首先通过视觉(如高亮PFD屏幕边框)、听觉(智能语音提醒)或触觉(驾驶杆震动)等手段唤醒飞行员;若无响应,系统将依据预设逻辑临时剥夺机长的操纵权限,无缝介入执行紧急避险拉起或转交控制权至地面的远程副驾驶中心。这种融合了人的生理极限、机器的物理边界以及深度学习算法预测的多源异构感知架构,构筑了未来商业航空SPO坚不可摧的安全底座。
在单机长体制(SPO)下,飞行员面临的最显著的负荷激增来源之一是通信任务。在传统的双人机组中,飞行(aviate)、导航(navigate)与通信(communicate)这三大核心任务通常由操纵飞行员(pilot flying,PF)和监控飞行员(pilot monitoring,PM)分担。PM负责监听甚高频(very high frequency,VHF)无线电、记录空中交通管制(air traffic control,ATC)的指令,并与机长进行交叉检查。当副驾驶被移除后,单名机长必须在复杂气象或高密度空域中,一边手动操纵飞机或管理自动飞行系统,一边独立应对高频的语音通信。这种任务叠加极易导致“听觉负荷超载”(auditory overload)和关键指令的遗漏或误解。因此,赋予AI副驾驶系统强大的自动语音识别(automatic speech recognition,ASR)与自然语言理解(NLU)能力,使其能够充当机长的“智能无线电操作员”与“全天候虚拟助理”,成为实现SPO不可或缺的技术基石。本节将深入探讨面向航空特有场景的智能语音交互技术,涵盖ATC专用语音识别模型、大模型驱动的语义理解,以及语音交互在驾驶舱内部程序执行中的应用。
商用通用语音识别系统(如苹果的Siri或各大云厂商的ASR接口)在日常生活场景中已达到极高的准确率,然而,当这些系统直接移植到航空驾驶舱环境中时,性能往往会遭遇灾难性的断崖式下降。导致这一现象的根本原因在于航空语音通信环境的极端特殊性。首先,航空陆空通话主要依赖甚高频(VHF)和高频(HF)模拟无线电波进行传输,信号在长距离传输中不可避免地受到电离层干扰、多径效应以及白噪声的污染,导致音频质量极差、信噪比(signal-to-noise ratio,SNR)极低;其次,尽管国际民航组织(International Civil Aviation Organization,ICAO)规定了标准化的“航空英语”(aviation English)(Estival等,2016),但在实际的高密度终端区运行中,管制员与飞行员为了抢占有限的波道,语速往往远超常人(有时高达每分钟200词以上);加之全球各地飞行员浓重的非母语口音、长句断句不规则,以及紧急情况下的非标准用语,使得传统声学模型面临极大的泛化挑战。
为了攻克这一行业壁垒,学术界与工业界深刻认识到,构建专用于航空领域的大规模标注数据集是训练鲁棒声学模型的先决条件。在这一领域,欧洲的多个大型联合研究项目取得了突破性进展。Zuluaga-Gomez等人(2020)首次针对空中交通管制通信提出了系统性的自动语音识别基准测试方案,揭示了通用模型在处理航空专用词汇(如特定航路点名称、五字代码、机型缩写)时的致命缺陷。在此基础上,研究团队进一步发布了具有里程碑意义的ATCO2语料库(Zuluaga-Gomez等,2024)。该数据集不仅收集了数百小时来自全球不同机场的真实空管通信音频,还创新性地结合了自动相关监视广播(automatic dependent surveillance-broadcast,ADS-B)的雷达数据,对音频中的航班号和情境信息进行了高度精确的半自动标注。
依托诸如ATCO2这类大规模专用数据集,新一代基于深度学习的端到端(end-to-end)声学模型在ATC语音识别任务上取得了质的飞跃。传统的混合架构(如GMM-HMM或DNN-HMM)逐渐被基于连接时序分类(connectionist temporal classification ,CTC)机制的深度模型(如Wav2Vec 2.0、conformer网络)所取代。这些先进模型利用自注意力机制(self-attention)和卷积神经网络(CNN)的结合,能够更好地捕捉无线电音频中长距离的时间依赖性和局部声学特征。通过在海量带噪语音上进行预训练,并在特定航空领域数据上进行微调(fine-tuning),当前的专用ASR模型已经能够将航空语音的词错误率(word error rate,WER)降低至可接受的个位数水平。更为重要的是,研究人员开始在模型中引入“上下文偏置”(contextual biasing)技术。由于空管通信具有极强的时空相关性(例如,在特定机场管区内,只会出现特定的进离场航路点和当前空域内的雷达航班号),ASR系统可以通过实时接入自动航行数据和ADS-B信息,动态调整声学解码器的语言模型概率。这种“物理情境增强”的识别机制,极大地提高了难以辨认的专有名词(callsigns,waypoints)的识别准确率,为后续的语义理解奠定了坚实而可靠的文本基础(Badrinath和Balakrishnan,2022)。
仅将嘈杂的无线电语音转化为文本(speech-to- text),对于减轻SPO机长的工作负荷而言是远远不够的。一段识别准确的文本串(如“Air China nine eight one,climb and maintain flight level three three zero,turn right heading zero four zero”)如果不能被机器解析为可执行的机器指令,机长依然需要用大脑去阅读、理解并手动输入到飞行控制面板(mode control panel,MCP)或飞行管理系统(FMS)中。因此,人工智能副驾驶必须具备深度的自然语言理解(NLU)能力,深刻剖析陆空通话背后的具体管制意图(intent recognition),并精准提取关键的飞行参数槽位(slot filling)。
航空指令的语义解析面临着许多独有的自然语言处理挑战。Lin(2021)在系统性总结空管口语指令理解时指出,真实的陆空通话中充斥着大量的口语化现象,如自我纠正(self-correction)(例如“下降到高度五千…纠正,保持六千”)、信息省略(省略呼号或单位),以及多重意图的复杂嵌套(一条语音内包含改变高度、改变航向和联系下一频率3个独立指令)。传统的基于正则表达式(Regex)或关键词匹配的浅层规则引擎在面对这种高度非结构化、充满歧义的口语文本时显得极其脆弱,极易发生灾难性的误触发或漏检。
随着以Transformer架构(Vaswani等,2017)为代表的大规模预训练语言模型(如BERT、GPT系列)的崛起,意图识别与参数提取的准确率和鲁棒性得到了革命性的提升。在航空NLU任务中,研究人员开始采用联合学习(joint learning)框架来同步解决这两个问题。例如,Deng等人(2023)提出了一种基于BERT架构的意图识别与槽位填充联合深度模型。该模型利用预训练大模型强大的双向上下文感知能力,能够在一个端到端的网络中同时输出整句指令的意图分类标签(如Altitude_Change,Heading_Change)以及每个词元(token)对应的槽位标签(如B-Callsign,I-Callsign,B-Altitude_ Value)。这种联合模型最大程度地利用了意图与槽位之间的强相关性特征(例如,当意图被判定为“调速”时,模型会自动更倾向于在句子中寻找“马赫数”或“节”相关的槽位值),有效解决了传统流水线模型(pipeline)中错误级联放大的问题。
当这种大模型驱动的语义理解引擎与飞机航电系统深度集成后,其对SPO体制的价值将是颠覆性的。AI副驾驶可以在监听到ATC指令后的毫秒级时间内,不仅将其转化为文本展示在平视显示器(HUD)上,更直接从文本中剥离出“航向:040”、“高度:33 000英尺”等关键参数,并自动将这些数据预填充至自动飞行控制系统的备用输入框中。单名机长只需进行快速的视觉确认,并在操纵杆上按下一个“执行/确认”按钮,飞机即可按照管制员的要求改变姿态与轨迹。这种从“手动听写 + 手动输入”向“AI自动解析 + 人工一键确认”的交互隐喻转变,使得人类飞行员从繁杂的数据搬运工真正回归到顶层决策管理者的角色,从根本上闭合了单人驾驶环境下的智能通信环路。
除了应对外部的空管通信,AI辅助驾驶技术在重塑驾驶舱内部交互逻辑,特别是程序性任务的执行方面同样发挥着不可替代的作用。在商用飞机的全飞行生命周期中,严格执行标准操作程序(standard operating procedure,SOP)和各类检查单(checklists)是保障航空安全的底线。在双人机组中,检查单的执行通常遵循严谨的“挑战—响应”(challenge-response)模式:PM大声朗读检查项目(例如“起落架”),PF进行物理操作或视觉确认后回应状态(例如“放下并锁定”)。在SPO环境下,由于缺乏物理上独立的第2个人来执行“挑战”动作,传统的纸质检查单或需要频繁手部操作的电子检查单(ECL)会严重分散机长的视觉注意力和操作精力。
以生成式人工智能为底座的智能对话语音助手正在彻底改变这一现状。目前,主流航空制造企业正致力于将类似于“ChatGPT”的认知辅助系统引入驾驶舱(Davidoff等,2024)。在常规飞行阶段(如起飞前准备、进近着陆准备),机载AI助理可以通过自然合成的语音(text to speech,TTS)主动充当PM的角色,逐条播报电子检查单的内容。更进一步的是,得益于飞机底层ARINC 429/664数据总线的连通,AI副驾驶并不需要机长口头回应每一个参数。它可以通过计算机视觉监控机长的手势,结合对飞机传感器数据的内部读取,自动判断襟翼角度或液压泵状态是否正常,从而实现半自动甚至全自动的检查单核对(Durach和Gutierrez,2024)。只有在关键安全节点或系统状态与要求不符时,语音助手才会主动发起语音警报,要求人类机长介入。国内的研究机构在此领域也进行了积极的工程化探索,郑晓庆和史万里(2025)成功开发并验证了基于人工智能的航空语音识别与交互软件,探讨了这种非接触式的人机交互手段在实际民航运行中降低人员工作负荷、提升作业标准化的显著效果。
更为关键的是,语音助手在面临非正常情况或紧急突发故障(non-normal/emergency procedures)时,展现出了挽救生命的巨大潜力。当飞机遭遇复合型系统失效(如客舱失压伴随发动机火警)时,机组通常需要查阅卷帙浩繁的快速参考手册(quick reference handbook,QRH)。在极度高压和恐慌的单人驾驶状态下,翻阅手册并准确定位对应的排故程序往往会耗费极其宝贵的时间,甚至引发致命的误操作。在此类极限场景下,具备高级语义检索能力的AI副驾驶成为关键的救命手段。飞行员只需通过自然语言发出紧急指令(例如“AI,立即调出二号发动机火警的记忆项目”),系统便能瞬间在庞大的飞行手册知识图谱中精准定位,不仅将最核心的排故步骤高亮投射至主飞行显示屏的显眼位置,更能以沉稳、清晰的合成语音同步指导机长执行关键的切断油路或释放灭火瓶操作。这种基于深度自然语言处理的即时交互能力,完美地弥补了单人在危机时刻记忆容量与信息检索速度的物理极限,使得AI副驾驶不仅是一个执行常规指令的工具,更升级为在绝境中提供认知托底的强大数字伙伴。
在单机长体制(SPO)的运行框架中,面对复杂多变的物理空域,仅仅依靠人类机长的经验或传统的自动飞行指引系统(AFDS)已难以应对高维度、高动态的突发状况。传统的自动驾驶仪主要依赖于飞行管理系统(FMS)中预先设定的静态航路点(waypoints)以及确定性的比例—积分—微分(PID)控制律,这种基于规则的系统在面对极端气象突变、严重系统故障或未知的空中交通冲突时,往往缺乏灵活性与自适应能力。为了在完全失去地面支持(如数据链中断)的极端情况下依然保障飞行安全,机载人工智能必须具备自主探索最优策略、进行动态航路重规划与冲突解算的高级决策能力。近年来,随着深度强化学习(deep reinforcement learning,DRL)理论的突破,以数据驱动和端到端学习为核心的智能规划算法在航空防撞系统与轨迹优化领域展现出了颠覆性的潜力。本节将深入探讨基于DRL的航路优化算法原理、多智能体协同避撞机制,以及在AI辅助下驾驶舱内人机控制权动态分配的底层逻辑。
在高度非结构化和不受约束的三维物理空域中,飞行器的轨迹规划本质上是一个典型的马尔可夫决策过程(Markov decision process,MDP)。在该框架下,智能体通过不断与环境交互,观察当前的状态(如位置、速度、姿态、风场信息),采取特定的动作(如调整俯仰角、滚转角或油门),并获得环境反馈的奖励(reward),其最终目标是最大化长期的累积奖励(Sutton和Barto,2018)。早期的强化学习算法(如Q-learning)在处理离散动作空间的游戏任务中取得了巨大成功(Mnih等,2015),但面对航空器连续的飞行动力学模型和高维度的状态空间时,往往面临严重的“维度灾难”问题。
为了突破连续控制的瓶颈,研究人员引入了基于Actor-Critic架构的深度强化学习算法。Lillicrap等人(2016)提出的深度确定性策略梯度(deep deterministic policy gradient,DDPG)算法首次将深度神经网络与确定性策略相结合,为连续动作空间的飞行控制奠定了基础。然而,在复杂多变的航空环境中,飞行轨迹的优化往往需要在燃油消耗、飞行时间、气象避让以及乘客舒适度等多重相互冲突的目标之间寻找帕累托最优(Pareto optimum)。针对这种高维、非线性的优化需求,近端策略优化(proximal policy optimization,PPO)(Schulman等,2017)和软性演员—评论家(soft actor-critic,SAC)(Haarnoja等,2018)等先进算法被广泛引入到航空智能规划领域。单纯的数据驱动型深度强化学习在面对分布外(out-of- distribution,OoD)的极端气象时,常面临探索空间爆炸与收敛困难。为此,当前的学术前沿正转向“大模型 + 强化学习”神经符号协同架构(neuro-symbolic architecture)。大模型凭借庞大的航空知识网络充当高级战略规划师(macro-planner),为系统提供情境理解与动态的奖励函数塑形(reward shaping);而PPO、SAC等算法则作为底层战术执行器(micro-actor),在连续动力学空间内生成高精度的避障轨迹,两者结合实现了大模型高维意图与底层动力学控制的完美闭环。PPO算法通过引入截断的代理目标函数(surrogate objective),限制了每次策略更新的幅度,从而在保证算法收敛稳定性的同时,极大提升了在复杂气象环境下的轨迹生成效率。而SAC算法则通过引入最大熵(maximum entropy)强化学习框架,不仅要求智能体最大化期望奖励,还要求其最大化策略的随机性,这使得飞机在面对未知风切变或局部雷暴等动态障碍时,展现出卓越的探索能力和极强的鲁棒性。不同的深度强化学习算法在复杂的航空避障中展现出截然不同的性能权衡。PPO作为同策略(on-policy)算法,其策略更新平滑且稳态误差极小,这在对安全性与稳定性要求极高的飞行控制中至关重要;但其样本效率较低,在面对极端未知气象时探索能力受限。相反,SAC作为异策略(off-policy)算法,通过引入最大熵机制显著增强了在复杂连续动作空间中的探索能力,在处理多机交汇等复杂场景下收敛速度更快、鲁棒性更强;但其代价是对超参数调优极其敏感,在非平稳气象环境下的控制平滑度略逊于PPO。各算法在动作空间支持、样本效率及训练稳定性等方面存在显著差异,适用场景各有侧重,如表1所示。其中,PPO因训练稳定性突出而广泛应用于飞行轨迹规划仿真;SAC在高维连续控制任务中样本效率更优;MARL虽然具备空地协同建模能力,但多智能体冲突解算的泛化困难仍是当前核心瓶颈。
在具体的工程应用层面,深度强化学习已被证明能够有效解决无约束环境下的动态导航问题。Chronis等人(2023)的研究表明,在不受传统航路结构限制的自由空域(free route airspace)中,强化学习算法能够综合评估实时的风速、风向和禁飞区限制,自主生成比传统启发式算法(如A*算法或遗传算法)更加平滑且燃油效率更高的三维轨迹。在国内研究方面,周彬等人(2021)针对无人机(unmanned aerial vehicle,UAV)提出一种基于导向强化学习的路径规划算法,通过引入人工势场法作为专家引导经验,显著加快了Q-learning在复杂障碍物环境中的收敛速度。尽管该研究最初面向无人机平台,但其底层的状态空间建模(融合了障碍物规避与目标点趋近)和奖励函数塑形机制,为大型商用客机在SPO模式下的自主避障提供了直接的理论参考。当飞机遭遇双发失效等极限情况,失去所有动力并急剧掉高时,基于DRL的机载AI助理能够在毫秒级时间内,利用潜在动力学模型(Hafner等,2020)在“潜在想象空间”中快速推演千万种可能的滑翔路径,并结合地形数据库自动规划出最优的迫降轨迹。这种超越人类极限的高维实时计算能力,是弥补单名飞行员在恐慌状态下认知计算能力不足的最有效技术手段。
随着城市空中交通(urban air mobility,UAM)概念的兴起以及传统商用空域航班密度的不断增加,单一智能体的航路规划已无法满足未来高密度空域的运行需求。当多架SPO客机或eVTOL(电动垂直起降飞行器)在狭窄的终端区或城市峡谷中交汇时,如果每架飞机都只基于自身的局部最优策略进行避让,极易引发连锁反应,导致空域的整体交通拥堵甚至发生空中相撞的灾难。因此,将空中交通管理(air traffic management,ATM)中的冲突解算与间隔保持任务建模为一个分布式协同决策问题,成为航空人工智能领域的另一大核心挑战。多智能体强化学习(multi-agent reinforcement learning,MARL)的引入,为实现去中心化的自主间隔保证(autonomous separation assurance)提供了革命性的解决方案。
在多机协同避让任务中,每架飞机的状态空间不仅包含自身的运动学参数,还需要实时接入通过ADS-B(广播式自动相关监视)接收到的周边入侵航空器的位置与意图信息。Wang等人(2022)对深度强化学习在空中交通管制冲突解算中的应用进行了全面回顾,指出传统的基于几何计算(如防撞系统TCAS(traffic alert and collision avoidance system))或冲突探测与解算(conflict detection and resolution,CD&R)规则的系统,在面对3架以上飞机同时发生冲突的复杂拓扑结构时,往往会陷入无解或发出相互矛盾的指令。相比之下,基于MARL的算法允许成百上千架飞机在虚拟仿真环境中进行数以亿次的自我博弈与试错。Brittain等人(2020)提出了一种深度的多智能体强化学习方法,专门用于解决高密度扇区内的自主间隔保证问题。在该架构下,各个智能体通过共享局部观测信息,学习到一种高度协同的隐式通信机制,能够在保持安全间隔的前提下,自动协调各机的速度调节与偏置机动,解算效率和全局最优性远超传统人类管制员的指挥极限。
针对更为复杂的城市低空空域,气流扰动剧烈且静态建筑物密布,战术冲突解算的难度呈指数级上升。Zhang等人(2023)针对无人驾驶航空器在城市空域中的运行,提出了一种基于注意力机制(attention-based)的深度强化学习战术冲突解算模型。该研究创新性地将Transformer架构中的自注意力机制与强化学习网络深度融合,使得机载AI能够在大范围的空域态势中,自动将计算资源“聚焦”于那些最具威胁的少数入侵航空器,从而在保证实时性的同时大幅提升了避撞决策的准确度。此外,Tonti等人(2025)在简化城市流场的导航研究中,也验证了深度强化学习在处理非线性流体力学干扰下的优异表现。不仅在空中,这种多智能体协同机制同样被延伸至机场地面的复杂滑行网络中。Szymanski等人(2023)探讨了如何利用单智能体和多智能体强化学习方法优化飞机的地面滑行轨迹,通过统筹规划多架飞机的推出和滑行路线,有效缓解了大型枢纽机场的地面拥堵,降低了燃油消耗。在更宏观的机场及空域协同维度上,将这种滑行轨迹重规划与基于航空大数据的航班延迟深度预测相结合,能够从全局视角显著提升整体运输网络的容错与周转效能(Gui等,2020)。在SPO环境下,这种全阶段(从地面滑行到高空巡航)的自主多机防撞网络,实质上构建了一个由机器智能主导的分布式安全气泡,极大地减轻了单名飞行员在拥挤空域中进行目视搜索与无线电协调的极高负荷(Sui等,2023)。
尽管深度强化学习在航路规划与冲突解算中展现出卓越的计算效能,但在民用航空这一极其强调“人类最终责任”的安全关键(safety-critical)领域,AI系统绝不能被设计为一个完全剥夺人类控制权的“独裁者”。相反,如何将AI的高效决策与人类飞行员的经验直觉深度融合,构建一个科学、平滑的人机协同(HAT)体系,是单机长体制必须跨越的人因工程鸿沟。在这个体系中,核心问题不再是“AI能做什么”,而是“控制权在何时、以何种方式在机长与AI之间进行动态分配与无缝接管”(dynamic function allocation)。
在传统的自动化设计中,权限的分配通常是静态且二元的(即自动驾驶仪要么完全接管,要么完全断开)。然而,Endsley(2017a)在总结人类与自动化交互研究的教训时深刻指出,这种刚性设计极易导致人类飞行员在紧急脱开时产生灾难性的“自动化惊奇”(automation surprise)和情境意识的完全丧失。为了克服这一缺陷,SPO架构下的AI副驾驶必须具备自适应的权限动态调节能力。Tokadlı等人(2021)在针对单人驾驶操作的域分析与需求定义中强调,动态权限分配必须建立在AI对飞行员当前心智状态(参考本文第2节的多模态状态监测)以及当前环境风险等级的精准实时评估之上。例如,在常规巡航且飞行员状态良好时,AI副驾驶处于底层的“被动监控与建议”模式(自动化程度较低),仅在背景进行航路寻优,并以文字或图形的形式在导航显示器上提供替代航路建议供机长选择。此时,决策权和执行权完全掌握在人类机长手中。
然而,当环境风险陡增或检测到机长状态异常时,系统的交互逻辑将发生根本性翻转。如果多模态传感器判定人类机长陷入了严重的疲劳或视觉隧道效应,且飞机正快速接近雷暴区,AI副驾驶将主动提升自身的自动化权限:首先发出强烈的听觉与触觉告警;若机长在预定时间窗口(如5 s)内未采取修正措施,AI副驾驶将依据DRL算法生成的避让轨迹,强行介入并驱动飞控系统执行规避机动。此时的接管逻辑不仅仅是一个机械的控制权切换,更涉及到复杂的人机信任(trust in automation)博弈。Lee和See(2004)在关于自动化信任的经典研究中指出,信任的校准对于避免对系统的“过度依赖”(over-reliance)或“弃用”(disuse)至关重要。如果AI频繁地进行不必要的误报或接管,将严重破坏单名飞行员对系统的信任基础。
因此,为了促进真正意义上的“队友般”的协作关系(teammate-likeness),AI在接管前后必须能够清晰地传达其意图的合理性(Wynne和Lyons,2018)。近期的航空人因学研究进一步指出,构建高效的航空人机团队必须考虑到诸如共享心理模型、透明沟通等团队科学的底层逻辑(Korentsides等,2024;Kirwan,2025)。在实际的系统设计中,这意味着AI副驾驶不仅需要执行避让机动,还需要通过智能语音系统向机长即时通报接管原因(如“机长,检测到正前方有严重风切变,您当前无响应,我已接管控制权并向右偏置20°”)。这种带有解释性和沟通性的动态权限分配机制,确保了在极端紧急情况下系统能够迅速止损,同时也最大程度地保障了人类飞行员在恢复状态后能够迅速重建情境意识并夺回控制权,从而构筑了单机长运行环境中人与机器互为冗余的终极安全防线。
在单机长体制(SPO)的愿景结构中,前面数节所探讨的状态感知、自然语言处理以及深度强化学习算法,从技术维度证明了“AI副驾驶”在实验室或模拟器环境下的卓越性能。然而,从技术可行性迈向商业化部署,横亘在航空工业界面前的是两座极其险峻的大山:一是飞行员在高度压力的物理座舱内如何对基于“黑盒”模型的机器决策建立科学、动态的信任;二是基于确定性逻辑构建的现代民航适航审定体系,如何接纳并认证具有“非确定性”与“自主演进”特征的数据驱动模型。本节将从人机信任危机的根源出发,系统综述可解释性人工智能(XAI)在航空领域的理论设计与应用探索,并深入剖析非确定性智能系统所面临的适航规章挑战及未来破局路径。
如图3所示,传统航空软件认证体系与AI/ML系统认证范式在开发理念、验证方法、可解释性要求、变更管控以及标准依据与监管现状5个维度上存在本质差异,其核心冲突在于:DO-178C要求对软件行为进行确定性合规证明,而AI系统行为由概率分布涌现,两者之间的范式鸿沟是SPO商业化的根本技术障碍。
现代人工智能技术,尤其是以多层人工神经网络为基础的深度学习(deep learning),其卓越的泛化能力与特征提取能力是以牺牲系统内部的逻辑透明度为代价的。这种称为“黑盒”(black-box)的特性意味着,即使是模型的设计者,也往往难以用人类可理解的自然语言精确反向溯源出模型得出某一特定结论的因果链条(Gunning和Aha,2019)。在消费级互联网应用中(如推荐系统或图像生成),偶尔的误判仅仅导致用户体验的轻微下降;然而,在航空这一典型的安全关键和时间紧迫(time-critical)的物理信息系统(cyber-physical systems)中,不可解释性将引发极其严重的人因工程灾难(Hoenig等,2024)。
在SPO运行环境下,人类机长被剥夺了与人类副驾驶进行逻辑探讨与决策交叉检查的物理途径。如果机载AI副驾驶突然在进近阶段指令飞机进行一次剧烈的复飞拉起或大坡度偏置,却无法立刻说明原因是由于检测到了肉眼不可见的微下击暴流(microburst)还是算法本身的传感器数据误读,单名飞行员将瞬间陷入严重的认知失调。Endsley(2017b)在对自动化失误的经典研究中指出,这种缺乏透明度的系统极易导致人类操作员发生“自动化惊奇”(automation surprise),不仅无法提供决策辅助,反而会彻底打断飞行员的OODA(观察—判断—决策—执行)认知环路,造成情境意识(SA)的灾难性丧失。近年来,大量的人机协同(HAT)研究表明,将AI作为驾驶舱内的虚拟队友,首要前提并非其计算性能的极致,而是其意图的可预测性与可解释性(Korentsides等,2024)。
这直接引出了人机交互领域的核心命题——“自动化信任”(trust in automation)。Lee和See(2004)在其奠基性文献中强调,信任的标准必须恰到好处:过度信任会导致飞行员对系统错误盲目顺从,最终引发类似于波音737 MAX MCAS系统失效时的惨剧;而信任不足(disuse 或 under-reliance)则会导致飞行员在紧急时刻拒绝使用高度先进的避险系统,增加工作负荷。在SPO环境下,动态且适度的信任建立完全依赖于AI系统的“透明度”(transparency)。Kirwan(2025)针对航空领域的AI协作指出,人类飞行员在将生死攸关的控制权移交给非人类实体时,潜意识中会要求该实体展现出类似于人类专家的推理逻辑。因此,打破深度学习的黑盒诅咒,将其转化为可理解的“灰盒”甚至“白盒”,不再是SPO系统锦上添花的加分项,而是确立人类最终决策权威、确保人机协同底线安全的核心技术先决条件(Yiu等,2026),设计“以人为中心”的机载人工认知系统,并针对SPO体制下的独有场景开展面向人工智能特征的系统级风险评估,成为打破黑盒信任危机的顶层设计基石(Ziakkas等,2025a,b)。
为了弥合高精度深度模型与人类认知需求之间的鸿沟,可解释性人工智能(XAI)技术在航空领域的应用正从基础理论向驾驶舱交互设计(UI/UX)加速渗透。XAI的核心目标是生成既能被非计算机专业的飞行员快速理解,又能在时间受限的紧急状况下不过度增加机长阅读负荷的解释输出(Sutthithatip等,2021)。目前,针对航空领域的XAI研究主要分为两大技术路线:“事后解释”(post-hoc explainability)与“内在可解释模型”(intrinsic interpretability)。
事后解释技术是指在不改变原有黑盒模型(如深层卷积神经网络或强化学习策略)内部结构的前提下,通过附加的算法逼近或可视化模型的决策依据。例如,利用局部可解释模型无关解释(local interpretable model-agnostic explanations,LIME)或沙普利加和解释(Shapley additive explanations,SHAP)算法。传统的事后解释技术(如显著性图)往往带来计算延迟,且难以用自然语言表达清晰的因果逻辑。大语言模型的思维链(chain-of-thought,CoT)推理能力为驾驶舱XAI带来了破局之道。 例如,在自动避障系统中,系统不再仅仅提供视觉热力图或僵硬的指令,而是依托大模型同步输出结构化的逻辑陈述(例如:检测到前方强对流雷暴,机长目前视觉闭眼时间超限,触发安全包线监控,执行右偏置20度避让)。这种基于大模型生成的自然语言因果反馈,结合PFD上的“线走廊”迹投射,极大地缓解了由于系统黑盒带来的自动化惊奇。在面向空管监控的系统开发中,Memon等人(2026)探讨了如何利用XAI技术对复杂的空中交通流进行监控预警。在驾驶舱内,如果AI副驾驶推荐了一条绕飞雷暴的新航路,XAI系统可以通过生成显著性图(saliency map)或热力图,在飞机的导航显示器上高亮标出迫使AI做出该决定的极端气象高风险像素区域。然而,事后解释技术在实际航空部署中面临着计算延迟的问题。在以毫秒为单位的战术冲突解算中,飞行员无法等待数十秒去阅读一份详尽的SHAP值贡献度图表。
因此,“操作化”的可解释性(operationalizing AI explainability)成为当前人机交互的前沿。Würfel等人(2024)深入探讨了如何通过“可解释性线索”(interpretability cues)将XAI无缝集成到驾驶舱显示中。他们在一项基于智能飞行员咨询系统(IPAS)的用户中心化开发实证研究中发现,飞行员在紧急情况下最需要的解释往往不是长篇大论的数学推理,而是直观的、上下文相关的视觉线索。例如,在自动避障系统中,XAI不应仅仅输出文字描述“左转20度”,而应在主飞行显示器(PFD)的3D合成视觉系统中,利用带颜色的“虚线走廊”投射出AI预测的安全飞行轨迹,并在旁边用极简的图标标注出(如“检测到未知无人机”)。这种设计遵循了“恰好够用”(just-in-time and just-enough)的信息呈现原则,确保机长能够在一瞥之间(glanceable)理解AI的“所见”与“所图”。此外,结合本文第3节提到的智能语音助手,XAI还可以通过自然语言反馈系统输出“因为…所以…”的逻辑陈述,这不仅极大缓解了机组资源管理(crew resource management,CRM)中由于缺失副驾驶导致的信息孤岛问题,更是维系单机长脑力模型(mental model)与系统实际状态高度对齐的关键。
即使通过XAI技术在驾驶舱前端解决了飞行员的主观信任问题,AI副驾驶的商业化应用还必须跨越一道法律与工程的硬性壁垒——航空适航认证(airworthiness certification)。航空业之所以能够保持极高的安全记录,归功于极其严苛且基于确定性逻辑的系统安全评估标准,如机载软件认证标准DO-178C、系统安全性评估标准ARP4754A等。然而,这套在过去半个世纪中被证明行之有效的标准体系,在面对现代机器学习(ML)模型时却面临着根本性的“范式冲突”。
传统航空软件认证遵循严格的V模型(V-model)开发流程,强调绝对的“可追溯性”(traceability)。开发人员必须证明代码的每一行都对应一个具体的高层需求,且面对相同的输入,系统必须在任何时候都产生完全相同且可预测的输出。相反,机器学习模型(尤其是深度强化学习)的本质是“数据驱动”而非“规则驱动”的。其控制逻辑并非由人类工程师显式编写,而是由神经网络的数百万个隐层权重通过海量数据训练涌现而来。这种非确定性(non-determinism)使得传统的代码覆盖率测试(如MC/DC)彻底失效,审查机构无法像审核传统自动驾驶仪的PID逻辑那样去验证一个深层神经网络的安全性(Crum等,2004)。正如Cummings和Britton(2020)在探讨安全关键自主系统监管时指出的那样,目前没有任何数学工具能够在一组有限的测试用例下,完全穷尽并证明深度学习模型在遭遇分布外的极端罕见情况(如黑天鹅事件)时不会发生灾难性的不可控输出。
面对这一适航死局,国际学术界与工业组织(如EASA和FAA)正积极探索针对SPO和人工智能特性的创新取证路径(Lim等,2017)。目前最具可行性的工程妥协方案是引入“运行时保障”(RTA)架构或单纯形架构(simplex architecture)。在这种架构下,复杂的、非确定性的AI副驾驶系统(称为“复杂主控制器”)与一个极其简单、高度确定性且已通过传统DO-178C最高安全等级认证的“备份监控器”(safety monitor)并列运行。AI系统负责在广阔的状态空间中生成高效的飞行策略,但其输出指令不直接作用于飞控系统;相反,所有指令必须先经过监控器的严格审查。一旦监控器判定AI的指令(如推力过大、俯仰角超过安全包线)违反了确定性的飞行动力学硬约束,RTA机制将立刻切断AI的控制权,并无缝倒换至传统的安全恢复控制律中。这种“将非确定性限制在安全边界内”(bounding the AI)的策略,使得监管机构在承认AI系统黑盒特性的同时,依然能够从系统级架构层面确保灾难性失效的概率低于10-9/飞行小时的严苛底线。上述从XAI方法、置信度量化到RTA运行时保障的完整适航技术路径如图4所示。
未来,随着神经网络形式化验证(formal verification)技术的成熟以及航空垂直领域大模型数据集标准化的建立,适航标准必将迎来一次深刻的重构,从而彻底打通AI技术从实验室走向单机长商业运营的法理通道。
在欧美适航政策的最新动向方面,监管机构正加速寻求破局之道。美国联邦航空管理局(Federal Aviation Administration,FAA)于2024年8月发布了首版《人工智能安全保障路线图》,明确提出了“渐进式、以安全为焦点”的认证路径,主张优先从降低机组负荷的低风险辅助系统起步,并探索基于运行时保障(RTA)的安全合规验证手段。同时,欧洲航空安全局(EASA)发布了《人工智能路线图2.0》,并启动了机器学习应用批准(MLEAP)研究项目。EASA确立了“以人为本”的AI信任构建模块,为Level 2(人机协同)级别的AI应用提供了首个概念性认证指南。这些政策动向释放了明确信号:未来的航空适航审定将不再强求对深度神经网络黑盒内部的绝对白盒化解释,而是转向构建“安全包线监控”与“数据质量审查”相结合的系统级安全性证明框架。
值得注意的是,在适航规章层面,针对EASA/FAA现有体系在应对非确定性系统时的局限性,中国民用航空局(Civil Aviation Administration of China,CAAC)及国内学术机构正积极探索符合中国民航运行特征的创新审定路径。国内学者针对商用飞机单一飞行员驾驶模式(SPO)的设计与测试进行了深入的本土化验证(张炯和曾锐,2020),致力于将深度学习模型的黑盒特征与传统航空工业的白盒测试标准相融合。此外,在航空智能系统的底层数据治理上,国内已率先开展基于航空标准质量的大模型数据集构建实践(裴育和何柳,2025)。这些研究不仅为国内SPO体制的商业化试飞提供了数据与理论依据,更为全球航空业建立具备共识性的航空人工智能适航标准体系贡献了中国方案。
单机长体制(SPO)作为下一代商业航空的战略制高点,其成功与否不仅取决于飞机物理硬件的冗余设计,更取决于能否构建一个足以弥补人类副驾驶缺位的“智能中枢”。本文系统回顾了近年来人工智能在辅助飞行员驾驶领域的理论演进、核心技术突破以及工程化面临的壁垒。本节将对全文的核心工作进行总结,深入剖析当前研究中存在的局限性,并对未来航空人工智能从单一算法向系统级人机深度协同的跨越提出前瞻性设想。
将先进的人工智能引入飞行座舱,代表了航空自动化理念从“被动辅助执行”向“主动认知协同”的深刻范式转移(Harris,2023)。本文围绕这一主线,全面梳理了构建AI副驾驶不可或缺的四大技术支柱:首先,在系统架构层面,建立融合机载独立算力与地面远程支援的空地一体化协同网络,是保障单人驾驶安全底线的关键前提。机载AI助理提供了微秒级的战术响应与断网冗余,而地面远程副驾驶则提供了全局战略视野,两者的深度互补构成了SPO运行的坚实骨架(Niermann等,2023)。其次,在人机交互的感知输入端,基于多模态异构融合的飞行员状态监测技术彻底改变了传统的主观负荷评估方式。利用时空图卷积网络对脑电图(EEG)的深度挖掘,以及基于近红外光谱(fNIRS)在真实飞行环境中的心智评估,结合非接触式的计算机视觉疲劳检测,使得AI系统能够实时、精准地捕捉机长在复杂任务中的认知负荷与注意狭窄(Gateau等,2018)。这种对“人类队友”的深度感知,是实现控制权动态无缝分配的先决条件。再次,在通信交互与程序执行方面,自然语言处理大模型在航空语音识别与语义理解中取得了突破性进展。依托如ATCO2等大规模航空专用数据集,基于Transformer等端到端架构的联合模型不仅克服了高噪声、非母语口音等声学障碍,更实现了管制指令意图的精准识别与飞行参数的自动提取预填(Zuluaga-Gomez等,2024;Deng等,2023)。这极大地重塑了驾驶舱的交互隐喻,大幅削减了单名机长的听觉与手动操作负荷。最后,在动态环境决策端,深度强化学习(如PPO、SAC算法)及其在多智能体强化学习(MARL)中的应用,使得飞行器能够在未知气象与高密度空域中自主生成安全、高效的三维避险轨迹。然而,研究也强烈表明,这些高效的数据驱动模型在实际部署时,面临着严峻的黑盒不可解释性危机以及现行确定性适航审定标准(如DO-178C)的合规性挑战(Yiu等,2026;Lim等,2017)。
尽管人工智能在单一航空任务节点上展现出了惊人的效能,但在迈向真实商业运营的进程中,仍存在诸多亟待解决的局限性:
1)航空领域的数据孤岛与“sim-to-real”泛化鸿沟。当前大多数深度学习模型的卓越表现高度依赖于特定实验室环境或高仿真飞行模拟器生成的数据集。然而,真实的航空运行数据(如各航空公司的QAR飞行数据、高保真机载传感器原始电信号)往往由于商业机密和数据安全壁垒,呈现出严重的“数据孤岛”现象。缺乏基于统一航空标准构建的高质量、大规模跨模态数据集,导致当前算法在面对真实世界中分布外的边缘场景(如极端雷暴伴随传感器失效)时,往往面临泛化能力崩溃的风险(裴育和何柳,2025)。
2)独立子任务的割裂与系统级融合的缺失。现有的学术研究多聚焦于孤立的单点技术突破,例如单纯优化语音识别的词错误率,或单纯提升冲突解算的收敛速度。但在真实的SPO座舱内,飞行员的决策是一个多源信息高度耦合的复杂过程。当前鲜有研究能够将视觉监控、语音交互、飞行动力学感知以及强化学习控制,统一集成到一个具备统一底层表示(unified representation)的全身心AI智能体中。这种模块间的割裂,极易在系统内部引发子系统之间的逻辑冲突。
3)系统透明度与人机信任机制依然脆弱。虽然可解释性人工智能(XAI)在航空领域开展了初步探索,但现有的“事后解释”方法大多会带来不可接受的计算延迟,且解释的形式往往过于学术,难以在几秒钟的危急时刻被非专业的飞行员快速吸收理解(Degas等,2022)。如果AI无法通过直观的座舱显控界面向人类机长传达其意图的合理性,人类不仅会拒绝交出控制权,甚至会因对抗系统而引发新的灾难(张炯和曾锐,2020)。
面向未来,航空人工智能的研究必须从“单一算法调优”向“系统级短板攻关”演进,具体应聚焦于突破前文所述的核心技术瓶颈:1)应对极端环境下的感知降级与多模态鲁棒性增强。 针对第2节揭示的非接触式视觉感知在座舱极端光照(如逆光、夜航)下面临的特征丢失问题,未来的感知基座亟需引入事件相机与热红外传感器的底层数据级融合;同时,针对fNIRS的时间滞后与EEG的易干扰性,需重点开发抗伪影的硬件级滤波与多模态时空对齐算法,确保在复杂颠簸环境下系统对飞行员状态的感知永不中断。2)突破多智能体强化学习的分布外泛化与绝对安全边界探索。 针对第4节指出的深度强化学习在多机冲突解算中的泛化困难,尤其是在面对分布外的极端气象或未知入侵航迹时,未来的研究应重点攻关“离线强化学习(offline RL)+ 安全屏蔽(safe shielding)”机制。通过引入基于物理信息的神经网络与动力学边界约束,确保MARL算法在进行高维战术寻优时,其生成的避撞轨迹绝对不会突破物理飞行包线,从而真正解决高密度城市空中交通和SPO交汇场景下的泛化安全痛点。
未来的研究应致力于打破文本、语音、视觉与传感序列的表征壁垒,将分散的感知、认知与决策模块融合为一个原生多模态的航空基座大模型(aviation foundation model)。大模型将不再仅仅是填补副驾驶职能的技术辅助工具,而是重塑单机长体制下人机信任基石、推动商用航空从“定性自动化执行”迈向“确定性智能协同”核心系统级引擎。这种模型能够同时“听”到空管指令、“看”到雷暴云图与机长的疲劳面容,并“感知”到当前的飞机姿态,从而在一个统一的潜在空间中进行联合推理,提供更加符合人类宏观直觉的全局决策建议。其次,推动可解释性与安全性设计的底层融合(safety and explainability by design)。未来的算法设计不应仅在黑盒模型外围打补丁,而应发展内在可解释的神经网络结构与形式化验证技术。例如,将飞行动力学的物理硬约束(如包线限制方程)直接内嵌至强化学习的损失函数或网络拓扑中,构建物理信息神经网络(physics-informed neural network,PINN)。同时,深入开展航空人因工程实验,探索在平视显示器(HUD)或合成视觉系统(synthetic vision system,SVS)中呈现“恰到好处”的视觉可解释性线索,建立健康、动态的人机信任模型(Ahmed,2025)。最后,重构基于数据驱动的适航审定框架。 工业界与学术界需紧密配合各国适航当局,制定针对自适应、非确定性机器学习模型的系统级安全评估新标准。在短期内,基于“运行时保障”(RTA)的降级架构将是推动AI上机的必由之路;而从长远来看,开发科学的模型鲁棒性量化指标与持续适航监控机制,将彻底打通单机长航班合法飞向蓝天的法理通道。
综上所述,人工智能副驾驶绝非剥夺人类飞行员的权威,而是旨在将人类从繁杂的体力操纵与信息过载中解放出来,使其跃升为全局系统的最高管理者与最终责任人。随着透明AI技术、人因协同理论以及适航标准的同频共振,人工智能必将补齐单机长体制的最后一块安全短板,重塑未来全球航空运输体系的新纪元。
  • 国家自然科学基金项目(62376217,62576279,62301434);中国科协青年人才托举工程项目(2023QNRC001)
参考文献 引证文献
排序方式:
Ahmed W. 2025. Artificial intelligence in aviation: a review of machine learning and deep learning applications for enhanced safety and security. Premier Journal of Artificial Intelligence,3(1): #100013 [DOI: 10.70389/PJAI.100013]
Alreshidi I,Moulitsas I and Jenkins K W. 2024. Advancing aviation safety through machine learning and psychophysiological data: a systematic review. IEEE Access,12: 5132-5150 [DOI: 10.1109/ACCESS.2024.3349495]
Arteaga R A. 2024. Artificial intelligence co-pilot for manned and unmanned aircraft. U.S.,No. 20,240,339,039
Badrinath S and Balakrishnan H. 2022. Automatic speech recognition for air traffic control communications. Transportation Research Record: Journal of the Transportation Research Board,2676(1): 798-810 [DOI: 10.1177/03611981211036359]
Banerjee C,Nguyen K,Fookes C and George K. 2025. Physics-informed computer vision: a review and perspectives. ACM Computing Surveys,57(1): #17 [DOI: 10.1145/3689037]
Banks S B and Lizza C S. 1991. Pilot’s associate: a cooperative,knowledge-based system application. IEEE Expert,6(3): 18-29 [DOI: 10.1109/64.87681]
Billings C E. 1991. Human-centered aircraft automation: a concept and guidelines. NASA Ames Research Center
Brittain M,Yang X X and Wei P. 2020. A deep multi-agent reinforcement learning approach to autonomous separation assurance [EB/OL]. [2026-04-16]. https://arxiv.org/pdf/2003.08353.pdf
Chen J W,Liu Y M,Cooke N and Tang P B. 2019. Real-time facial expression and head pose analysis for monitoring the workloads of air traffic controllers//Proceedings of 2019 AIAA Aviation Forum. Dallas,USA: AIAA: #3412 [DOI: 10.2514/6.2019-3412]
Chen J Y C and Barnes M J. 2014. Human-agent teaming for multirobot control: a review of human factors issues. IEEE Transactions on Human-Machine Systems,44(1): 13-29 [DOI: 10.1109/THMS.2013.2293535]
Chen W L,Wagner J,Heugel N,Sugar J,Lee Y W,Conant L,et al. 2020. Functional near-infrared spectroscopy and its clinical application in the field of neuroscience: advances and future directions. Frontiers in Neuroscience,14: #724 [DOI: 10.3389/fnins.2020.00724]
Chronis C,Anagnostopoulos G,Politi E,Dimitrakopoulos G and Varlamis I. 2023. Dynamic navigation in unconstrained environments using reinforcement learning algorithms. IEEE Access,11: 117984-118001 [DOI: 10.1109/ACCESS.2023.3326435]
Crum V,Homan D and Bortner R. 2004. Certification challenges for autonomous flight control systems//Proceedings of 2004 AIAA Guidance,Navigation,and Control Conference and Exhibit. Providence,USA: AIAA: #5257 [DOI: 10.2514/6.2004-5257]
Cummings M L and Britton D. 2020. Regulating safety-critical autonomous systems: past,present,and future perspectives//Pak R,de Visser E J and Rovira E,eds. Living With Robots. Amsterdam: Elsevier: 119-140 [DOI: 10.1016/B978-0-12-815367-3.00006-2]
Davidoff A,Vonderhaar L,Caldwell A,Procko T and Ochoa O. 2024. Role,needs,and state of cognitive assistants in single-pilot operations. Journal of Aerospace Information Systems,21(12): 1014-1024 [DOI: 10.2514/1.I011432]
Debie E,Rojas R F,Fidock J,Barlow M,Kasmarik K,Anavatti S,et al. 2021. Multimodal fusion for objective assessment of cognitive workload: a review. IEEE Transactions on Cybernetics,51(3): 1542-1555 [DOI: 10.1109/TCYB.2019.2939399]
Degas A,Islam M R,Hurter C,Barua S,Rahman H,Poudel M,et al. 2022. A survey on artificial intelligence (AI) and explainable AI in air traffic management: current trends and development with future research trajectory. Applied Sciences,12(3): #1295 [DOI: 10.3390/app12031295]
Deng Q H,Yang Y,Zhang X X,Qian S S,Zhang M H and Cai K Q. 2023. A BERT-based intent recognition and slot filling joint model for air traffic control instruction understanding//Proceedings of the 42nd IEEE/AIAA Digital Avionics Systems Conference. Barcelona,Spain: IEEE: 1-9 [DOI: 10.1109/DASC58513.2023.10311266]
Durach C F and Gutierrez L. 2024. “Hello,this is your AI co-pilot”—operational implications of artificial intelligence chatbots. International Journal of Physical Distribution and Logistics Management,54(3): 229-246 [DOI: 10.1108/IJPDLM-01-2024-0031]
Dzreke S S. 2025. The AI co-pilot: navigating market turbulence and charting a course for sustainable advantage. International Journal of Management Science and Application,4(2): 67-94 [DOI: 10.58291/ijmsa.v4i2.442]
Endsley M R. 2017a. From here to autonomy: lessons learned from human — automation research. Human Factors: The Journal of the Human Factors and Ergonomics Society,59(1): 5-27 [DOI: 10.1177/0018720816681350]
Endsley M R. 2017b. Toward a theory of situation awareness in dynamic systems//Salas E,ed. Situational Awareness. London: Routledge: 9-42
Estival D,Farris C and Molesworth B. 2016. Aviation English: A Lingua Franca for Pilots and Air Traffic Controllers. London: Routledge [DOI: 10.4324/9781315661179s]
Flores A,Paselk A and McAndrew I. 2024. Advancing perspectives: a scoping review of artificial intelligence applications in aviation human factors for flight crews//Proceedings of 2024 AHFE International Conference on Human Factors in Design,Engineeing,and Conputing. Hawaii,USA: AHFE International: 2149-2163 [DOI: 10.54941/ahfe1005783]
Gateau T,Ayaz H and Dehais F. 2018. In silico vs. over the clouds: on-the-fly mental state estimation of aircraft pilots,using a functional near infrared spectroscopy based passive-BCI. Frontiers in Human Neuroscience,12: #187 [DOI: 10.3389/fnhum.2018.00187]
Gui G,Liu F,Sun J L,Yang J,Zhou Z Q and Zhao D X. 2020. Flight delay prediction based on aviation big data and machine learning. IEEE Transactions on Vehicular Technology,69(1): 140-150 [DOI: 10.1109/TVT.2019.2954094]
Gunning D and Aha D W. 2019. DARPA’s explainable artificial intelligence program. AI Magazine,40(2): 44-58 [DOI: 10.1609/aimag.v40i2.2850]
Haarnoja T,Zhou A,Abbeel P and Levine S. 2018. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor//Proceedings of the 35th International Conference on Machine Learning. Stockholm,Sweden: PMLR: 1861-1870
Hafner D,Lillicrap T,Ba J and Norouzi M. 2020. Dream to control: learning behaviors by latent imagination//Proceedings of the 8th International Conference on Learning Representations. Addis Ababa,Ethiopia: OpenReview.net
Harris D. 2007. A human-centred design agenda for the development of single crew operated commercial aircraft. Aircraft Engineering and Aerospace Technology,79(5): 518-526 [DOI: 10.1108/00022660710780650]
Harris D. 2023. Single-pilot airline operations: designing the aircraft may be the easy part. The Aeronautical Journal,127(1313): 1171-1191 [DOI: 10.1017/aer.2022.110]
He K M,Zhang X Y,Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90]
Hoenig A,Roy K,Acquaah Y T,Yi S and Desai S S. 2024. Explainable AI for cyber-physical systems: issues and challenges. IEEE Access,12: 73113-73140 [DOI: 10.1109/ACCESS.2024.3395444]
Hörhager P. 2025. Aircraft Automation and Human Performance: An Analysis of Flight Deck Failures. Wien,Austria: Technische Universität Wien [DOI: 10.34726/hss.2025.84080]
Husain A M. 2025. Of pilots and copilots: the evolving role of artificial intelligence in clinical neurophysiology. The Neurodiagnostic Journal,65(1): 2-12 [DOI: 10.1080/21646821.2025.2465089]
Kirwan B. 2025. Human factors requirements for human-AI teaming in aviation. Future Transportation,5(2): #42 [DOI: 10.3390/futuretransp5020042]
Korentsides M S J,Keebler J R,Fausett C M,Patel S M and Lazzara E H. 2024. Human-AI teams in aviation: considerations from human factors and team science. Journal of Aviation/Aerospace Education and Research,33(4): #7 [DOI: 10.58940/2329-258X.2046]
Koul P. 2025. A review of machine learning applications in aviation engineering. Advances in Mechanical and Materials Engineering,42(1): 16-40 [DOI: 10.7862/rm.2025.2]
Kuang W T,Mao K C,Huang J C and Li H B. 2016. Fatigue driving detection based on sclera Gaussian model. Journal of Image and Graphics,21(11): 1515-1522
旷文腾,毛宽诚,黄家才,李海彬. 2016. 基于高斯眼白模型的疲劳驾驶检测. 中国图象图形学报,21(11): 1515-1522 [DOI: 10.11834/jig.20161111]
Lee J D and See K A. 2004. Trust in automation: designing for appropriate reliance. Human Factors: The Journal of the Human Factors and Ergonomics Society,46(1): 50-80 [DOI: 10.1518/hfes.46.1.50_30392]
Lei H J and Yao C K. 2020. Technical architecture of aviation artificial intelligence for military application. Navigation Positioning and Timing,7(1): 1-11
雷宏杰,姚呈康. 2020. 面向军事应用的航空人工智能技术架构研究. 导航定位与授时,7(1): 1-11 [DOI: 10.19306/j.cnki.2095-8110.2020.01.001]
Lillicrap T P,Hunt J J,Pritzel A,Heess N,Erez T,Tassa Y,et al. 2016. Continuous control with deep reinforcement learning//Proceedings of the 4th International Conference on Learning Representations. San Juan,Puerto Rico,USA: ICLR [DOI: 10.48550/arXiv.1509.02971]
Lim Y,Bassien-Capsa V,Ramasamy S,Liu J and Sabatini R. 2017. Commercial airline single-pilot operations: system design and pathways to certification. IEEE Aerospace and Electronic Systems Magazine,32(7): 4-21 [DOI: 10.1109/MAES.2017.160175]
Lin Y. 2021. Spoken instruction understanding in air traffic control: challenge,technique,and application. Aerospace,8(3): #65 [DOI: 10.3390/aerospace8030065]
Lu X L,Du Z L and Xu Y. 2021. Review on basic concept and applications for artificial intelligence in aviation. Acta Aeronautica et Astronautica Sinica,42(4): #525150
卢新来,杜子亮,许赟. 2021. 航空人工智能概念与应用发展综述. 航空学报,42(4): #525150 [DOI: 10.7527/S1000-6893.2021.25150]
Memon M,Narejo S,Talpur S,Channa A,Mangi F A and Pandey J K. 2026. Explainable AI (XAI) in air traffic monitoring systems//Pandey J K,Rai M,Ahmad F,eds. Machine Learning based Air Traffic Surveillance System Using Image Processing. Bingley: Emerald Publishing Limited: 21-39 [DOI: 10.1108/978-1-80592-062-520251002]
Mnih V,Kavukcuoglu K,Silver D,Rusu A A,Veness J,Bellemare M G,et al. 2015. Human-level control through deep reinforcement learning. Nature,518(7540): 529-533 [DOI: 10.1038/nature14236]
Niermann C,Ebrecht L,Küls J,Findeisen M S and Hofmann T. 2023. Development process for a remote co-pilot to support single-pilot operation in a next-generation air transportation system//Proceedings of the 14th International Conference on Applied Human Factors and Ergonomics and the Affiliated. San Francisco,USA: AHFE International: 1-11 [DOI: 10.54941/ahfe1003914]
Pei Y and He L. 2025. Research on the construction technology of high-quality datasets for aviation standard quality large models. Aeronautic Standardization and Quality,(6): 52-56
裴育,何柳. 2025. 基于航空标准质量大模型数据集高质量构建实践. 航空标准化与质量,(6): 52-56 [DOI: 10.13237/j.cnki.asq.2025.06.11]
Redmon J,Divvala S,Girshick R and Farhadi A. 2016. You only look once: unified,real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA: IEEE: 779-788 [DOI: 10.1109/CVPR.2016.91]
Schulman J,Wolski F,Dhariwal P,Radford A and Klimov O. 2017. Proximal policy optimization algorithms [EB/OL]. [2026-04-14]. https://arxiv.org/pdf/1707.06347.pdf
Shi Z H,Wu C W,Li C J,You Z Z,Wang Q and Ma C C. 2023. Object detection techniques based on deep learning for aerial remote sensing images: a survey. Journal of Image and Graphics,28(9): 2616-2643
石争浩,仵晨伟,李成建,尤珍臻,王泉,马城城. 2023. 航空遥感图像深度学习目标检测技术研究进展. 中国图象图形学报,28(9): 2616-2643 [DOI: 10.11834/jig.221085]
Sridhar B. 2020. Applications of machine learning techniques to aviation operations: promises and challenges//Proceedings of 2020 International Conference on Artificial Intelligence and Data Analytics for Air Transportation. Singapore,Singapore: IEEE: 1-12 [DOI: 10.1109/AIDA-AT48540.2020.9049205]
Stanton N A,Stewart R,Harris D,Houghton R J,Baber C,McMaster R,et al. 2006. Distributed situation awareness in dynamic systems: theoretical development and application of an ergonomics methodology. Ergonomics,49(12/13): 1288-1311 [DOI: 10.1080/00140130600612762]
Sui D,Ma C Y and Dong J T. 2023. Conflict resolution strategy based on deep reinforcement learning for air traffic management. Aviation,27(3): 177-186 [DOI: 10.3846/aviation.2023.19720]
Sutthithatip S,Perinpanayagam S,Aslam S and Wileman A. 2021. Explainable AI in aerospace for enhanced system performance//Proceedings of the 40th IEEE/AIAA Digital Avionics Systems Conference. San Antonio,USA: IEEE: 1-7 [DOI: 10.1109/DASC52595.2021.9594488]
Sutton R S and Barto A G. 2018. Reinforcement Learning: An Introduction. 2nd ed. Cambridge,USA: The MIT Press
Szymanski M,Ghazi G and Botez R M. 2023. Single and multi-agent reinforcement learning approach to optimize aircraft ground trajectories at airports//Proceedings of 2023 Aerospace Europe Conference. Lausanne: EUCASS: 1-14 [DOI: 10.13009/EUCASS2023-713]
Tao J H,Wu Y C,Yu C,Weng D D,Li G J,Han T,et al. 2022. A survey on multi-modal human-computer interaction. Journal of Image and Graphics,27(6): 1956-1987
陶建华,巫英才,喻纯,翁冬冬,李冠君,韩腾,等. 2022. 多模态人机交互综述. 中国图象图形学报,27(6): 1956-1987 [DOI: 10.11834/jig.220151]
Tokadlı G,Dorneich M C and Matessa M. 2021. Toward human-autonomy teaming in single-pilot operations: domain analysis and requirements. Journal of Air Transportation,29(4): 142-152 [DOI: 10.2514/1.D0240]
Tonti F,Rabault J and Vinuesa R. 2025. Navigation in a simplified urban flow through deep reinforcement learning. Journal of Computational Physics,538: #114194 [DOI: 10.1016/j.jcp.2025.114194]
Vaswani A,Shazeer N,Parmar N,Uszkoreit J,Jones L,Gomez A N,et al. 2017. Attention is all you need//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach,USA: Curran Associates Inc.: 6000-6010
Wang Y S,Guo X Y,Guo S S,Jiang F,Liang Z P,Peng L,et al. 2025. Machine learning evaluation model of pilot workload in a low-visibility environment. Scientific Reports,15(1): #20518 [DOI: 10.1038/s41598-025-05759-7]
Wang Z,Pan W J,Li H,Wang X and Zuo Q H. 2022. Review of deep reinforcement learning approaches for conflict resolution in air traffic control. Aerospace,9(6): #294 [DOI: 10.3390/aerospace9060294]
Würfel J,Papenfuß A and Wies M. 2024. Operationalizing AI explainability using interpretability cues in the cockpit: insights from user-centered development of the intelligent pilot advisory system (IPAS)//Proceedings of the 5th International Conference on Artificial Intelligence in HCI,AI-HCI 2024,held as part of the 26th International Conference. Washington,USA: Springer: 297-315 [DOI: 10.1007/978-3-031-60606-9_17]
Wynne K T and Lyons J B. 2018. An integrative model of autonomous agent teammate-likeness. Theoretical Issues in Ergonomics Science,19(3): 353-374 [DOI: 10.1080/1463922X.2016.1260181]
Xu X F,Gao Y J and Liu Z. 2020. Research on the application of artificial intelligence technology in flight test//Proceedings of the 17th China Aviation Measurement and Control Technology Annual Conference. Xi’an: National Defense Technology Industry Automation Testing Innovation Center: 41-44
徐小芳,高雅娟,刘钊. 2020. 人工智能技术在飞行试验中的应用研究//第十七届中国航空测控技术年会论文集. 西安: 国防科技工业自动化测试创新中心: 41-44 [DOI: 10.26914/c.cnkihy.2020.027547]
Yiu C Y,Li W C,Ng K K H,Chi C F and Schiefele J. 2026. Enhancing aviation safety with artificial intelligence: a systematic literature review on recent advances,challenges and future perspectives. Advanced Engineering Informatics,71: #104378 [DOI: 10.1016/j.aei.2026.104378]
Zhang J and Zeng R. 2020. Mode design and test for commercial aircraft single-pilot operations. Aeronautical Science and Technology,31(6): 42-49
张炯,曾锐. 2020. 商用飞机单一飞行员驾驶模式设计及测试. 航空科学技术,31(6): 42-49 [DOI: 10.19452/j.issn1007-5453.2020.06.007]
Zhang M C,Yan C,Dai W,Xiang X J and Low K H. 2023. Tactical conflict resolution in urban airspace for unmanned aerial vehicles operations using attention-based deep reinforcement learning. Green Energy and Intelligent Transportation,2(4): #100107 [DOI: 10.1016/j.geits.2023.100107]
Zheng X Q and Shi W L. 2025. An aviation speech recognition system software based on artificial intelligence and its application. Journal of Civil Aviation,9(3): 92-96
郑晓庆,史万里. 2025. 一种基于人工智能的航空语音识别系统软件及应用. 民航学报,9(3): 92-96 [DOI: 10.3969/j.issn.2096-4994.2025.03.018]
Zhou B,Guo Y,Li N and Zhong X J. 2021. Path planning of UAV using guided enhancement Q-learning algorithm. Acta Aeronautica et Astronautica Sinica,42(9): 325109
周彬,郭艳,李宁,钟锡健. 2021. 基于导向强化Q学习的无人机路径规划. 航空学报,42(9): #325109 [DOI: 10.7527/S1000-6893.2021.25109]
Ziakkas D,Henneberry D and Plioutsias A. 2025a. Designing human-centric intelligent systems in aviation: applications of artificial cognitive systems,AI-enhanced investigations,and immersive eVTOL simulation training. Human-Intelligent Systems Integration,7(1): 249-262 [DOI: 10.1007/s42454-025-00083-x]
Ziakkas D,Pechlivanis K and Plioutsias A. 2025b. Enhancing aviation risk assessment through artificial intelligence: the single pilot operations case study. Transportation Research Procedia,88: 305-314 [DOI: 10.1016/j.trpro.2025.05.037]
Zuluaga-Gomez J,Motlicek P,Zhan Q R,Veselý K and Braun R. 2020. Automatic speech recognition benchmark for air-traffic communications//Proceedings of the 21st Annual Conference of the International Speech Communication Association. Shanghai,China: ISCA: 2297-2301 [DOI: 10.21437/Interspeech.2020-2173]
Zuluaga-Gomez J,Veselý K,Szöke I,Blatt A,Motlicek P,Kocour M,et al. 2024. ATCO2 corpus: a large-scale dataset for research on automatic speech recognition and natural language understanding of air traffic control communications. Journal of Data-Centric Machine Learning Research,2(5): 1-45
2026年第31卷第9期
PDF下载
26
13
引用本文
BibTeX
文章信息
doi: 10.11834/jig.260216
  • 接收时间:2026-04-16
  • 首发时间:2026-10-30
  • 出版时间:2026-09-16
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-04-16
  • 修回日期:2026-05-19
基金
National Natural Science Foundation of China (62376217,62576279,62301434);Young Elite Scientists Sponsorship Program by CAST(2023QNRC001)
国家自然科学基金项目(62376217,62576279,62301434);中国科协青年人才托举工程项目(2023QNRC001)
作者信息
    1 西北工业大学计算机学院,西安 710129
    2 沈阳飞机设计研究所,沈阳 110035
    3 西北工业大学卓越工程师学院,西安 710072
    4 清华大学航天航空学院,北京 100084
    5 西北工业大学电子信息学院,西安 710129

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.260216
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏