智能化农业装备学报（中英文）

果园作业机器人自主导航多任务联合感知方法研究

预览PDF | 下载PDF

张津国 ¹^,² , 蔡建峰 ¹^,² , 姜蓉蓉 ³ , 余山山 ⁴ , 王蓬勃 ¹^,²^,^*^,^*

智能化农业装备学报（中英文） | 2025,6(2): 35-43

收起

智能化农业装备学报（中英文） | 2025 , 6 (2) : 35 -43

果园作业机器人自主导航多任务联合感知方法研究

全屏

张津国¹^,², 蔡建峰¹^,², 姜蓉蓉³, 余山山⁴, 王蓬勃¹^,²^,^*^,^*

作者信息

^1.苏州大学机电工程学院，江苏苏州，215137

^2.江苏省具身智能机器人技术重点实验室，江苏苏州，215137

^3.苏州漕阳生态农业发展有限公司，江苏苏州，215143

^4.农业农村部南京农业机械化研究所，江苏南京，210014

通讯作者:

^* 王蓬勃，男，1984年生，安徽阜阳人，博士，副教授；研究方向为农业机器人、农业人工智能。E-mail：pbwang@suda.edu.cn

作者简介:

张津国，男，2000年生，江苏连云港人，硕士研究生；研究方向为农业机器人导航技术。E-mail：20225229128@stu.suda.edu.cn

Multi-task joint perception framework for autonomous navigation in orchard robotics

Jinguo ZHANG¹^,², Jianfeng CAI¹^,², Rongrong JIANG³, Shanshan YU⁴, Pengbo WANG¹^,²

Affiliations

^1.College of Mechanical and Electrical Engineering, Soochow University, Suzhou 215137, China

^2.Jiangsu Key Laboratory of Embodied Intelligent Robot Technology, Suzhou 215137, China

^3.Suzhou Caoyang Ecological Agriculture Development Co., Ltd., Suzhou 215143, China

^4.Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China

Corresponding Author:

^* WANG Pengbo, E-mail: zhulixue@zhku.edu.cn

ZHANG Jinguo, E-mail: 1432263736@qq.com

出版时间: 2025-05-15 doi: 10.12398/j.issn.2096-7217.2025.02.003

文章导航

摘要

收起

针对果园复杂作业场景中植被异质性高、光照动态变化显著以及目标形态多样性等挑战，传统基于单任务学习的视觉感知模型因特征复用率低、计算冗余度高等问题，难以满足农业机器人实时环境感知需求。本研究提出一种面向果园场景的轻量化多任务联合感知框架AgriYOLOP，通过系统性地重构YOLOP网络架构，引入高效的主干网络，并添加增强的无锚检测技术以及增加了特征金字塔网络和路径聚合网络，并设计任务自适应的损失函数权重策略，实现树干检测、障碍物识别与可通行区域分割的并行化协同处理。在自主构建的果园数据集中进行验证，该数据集包含果园场景下4 765张分辨率为1 280像素×720像素的图像，涵盖不同季节、光照条件及植被生长阶段。试验结果表明，AgriYOLOP模型在目标检测任务中检测准确率、召回率以及mAP50分别达到92.7%、94.6%以及96.7%，在可行区域分割任务下召回率、F1分数以及mIoU达到98.3%、99.1%、98.1%，在NVIDIA RTX 4060平台下实现69f/s的实时推理速度，模型参数量仅14 M。对比结果表明，多任务协同学习架构能够显著提升特征共享效率，较单任务模型减少32.6%推理延迟，同时增强了对光照变化与季节特征的鲁棒性，有效地解决了农业机器人实时作业场景中目标检测精度与语义分割效率的协同优化难题。本研究为果园机器人自主导航提供了高精度、低延迟的实时感知解决方案。

关键词

多任务学习 / 果园环境感知 / 目标检测 / 语义分割 / 农业机器人

Abstract

收起

Orchard operational scenarios present significant challenges for visual perception, including high vegetation heterogeneity, dynamic lighting variations, and diverse target morphologies. Traditional single-task visual perception models suffer from low feature reusability and high computational redundancy, thereby inadequately addressing real-time environmental perception demands for agricultural robots. This study proposes AgriYOLOP, a lightweight multi-task collaborative perception framework specifically designed for orchard environments. Through a systematic reconstruction of the YOLOP architecture, AgriYOLOP incorporates an efficient backbone network, enhanced anchor-free detection techniques, feature pyramid networks (FPN), path aggregation networks (PAN), and task-adaptive loss function weighting strategies. This framework faciliates parallel collaborative processing of three critical percetption tasks: trunk detection, obstacle recognition, and traversable region segmentation. The proposed framework was validated on a self-constructed orchard dataset comprising 4 765 images (1 280 pixels×720 pixels), captured across diverse seasons, lighting conditions, and vegetation growth stages. Experimental results demonstrate that AgriYOLOP achieves 92.7% precision, 94.6% recall, and 96.7% mAP50 in object detection tasks, along with 98.3% recall, 99.1 F1 score, and 98.1% mIoU in traversable region segmentation. Deployed on an NVIDIA RTX 4060 platform, the model attains 69 f/s real-time inference speed with only 14 M parameters. Comparative experiments reveal that the multi-task collaborative architecture significantly enhances feature-sharing efficiency, reducing inference latency by 32.6% compared to single-task models while improving robustness to illumination and seasonal variations. This approach effectively mitigates the conventional trade-off between target detection accuracy and semantic segmentation efficiency encountered in real-time agricultural robotic applications. The study provides a high-precision, low-latency real-time perception solution for autonomous orchard robot navigation.

Key words

multi-task learning / orchard environment perception / target detection / semantic segmentation / agricultural robot

引用本文

张津国, 蔡建峰, 姜蓉蓉, 余山山, 王蓬勃. 果园作业机器人自主导航多任务联合感知方法研究. 智能化农业装备学报（中英文）, 2025 , 6 (2) : 35 -43 . DOI: 10.12398/j.issn.2096-7217.2025.02.003

Jinguo ZHANG, Jianfeng CAI, Rongrong JIANG, Shanshan YU, Pengbo WANG. Multi-task joint perception framework for autonomous navigation in orchard robotics[J]. Journal of Intelligent Agricultural Mechanization, 2025 , 6 (2) : 35 -43 . DOI: 10.12398/j.issn.2096-7217.2025.02.003

基金

收起

国家重点研发计划项目(2022YFB4702202)
江苏省农业农村厅农机研发制造推广应用一体化试点项目(JSYTH07)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

张隆梅，刘岗微，齐彦栋，等．农业机械无人驾驶系统关键技术研究进展（英文）[J]．智能化农业装备学报（中英文），2022，3（1）：27-36.

ZHANG Longmei, LIU Gangwei, QI Yandong, et al. Research progress on key technologies of agricultural machinery unmanned driving system [J]. Journal of Intelligent Agricultural Mechanization, 2022, 3(1): 27-36.

[2]

刘羊，刘宇洋，陈江春，等．标准化果园多功能作业平台关键技术研究现状与趋势[J]．智能化农业装备学报（中英文），2024，5（1）：31-39.

LIU Yang, LIU Yuyang, CHEN Jiangchun, et al. Research status and trend of key technologies of standardized orchard multi-functional operation platform [J]. Journal of Intelligent Agricultural Mechanization, 2024, 5(1): 31-39.

[3]

李建平，李绍波，杨欣，等．苹果园生产管理智能机械化技术与装备研究进展与展望[J]．智能化农业装备学报（中英文），2024，5（4）：66-83.

LI Jianping, LI Shaobo, YANG Xin, et al. Research progress on intelligent mechanization technology and equipment for apple orchard production management [J]. Journal of Intelligent Agricultural Mechanization, 2024, 5(4): 66-83.

[4]

张翼．中国式现代化的推进、人口转型与弹性退休制度[J]．北京大学学报（哲学社会科学版），2024，61（5）：128-136.

ZHANG Yi. Promotion of chinese-style modernization, population transformation and flexible retirement system [J]. Journal of Peking University (Philosophy and Social Sciences), 2024, 61(5): 128-136.

[5]

王文明，王志强，韩明明，等．我国智慧果园关键技术装备研究应用现状与展望[J]．中国果树，2024（7）：143-149.

[6]

朱云，凌志刚，张雨强．机器视觉技术研究进展及展望[J]．图学学报，2020，41（6）：871-890

[7]

REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis &Machine Intelligence, 2017, 39(6): 1137-1149.

[8]

CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]// European conference on computer vision. Cham: Springer International Publishing, 2020.

[9]

REDMON J, FARHADI A. YOLO9000: Better, faster, stronger [J]. IEEE, 2017: 6517-6525.

[10]

BENJUMEA A, TEETI I, CUZZOLIN F, et al. YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles [J]. 2021.

[11]

HUANG Z, WANG J, FU X, et al. DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection [J]. Information Sciences, 2020, 522.

[12]

CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs [J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40(4): 834-848.

[13]

WENG W, ZHU X. INet: Convolutional networks for biomedical image segmentation [J]. IEEE Access, 2021, 9: 16591-16603.

[14]

LI H, XIONG P, FAN H, et al. Dfanet: Deep feature aggregation for real-time semantic segmentation [C]//Proceedings of the IEE E/CVF conference on computer vision and pattern recognition, 2019: 9522-9531.

[15]

GUO Y, ASHMAWY K, HUANG E, et al. Under the hood of uber atg's machinelearning infrastructure and versioning control platform for self-driving vehicles [J]. Uber Engineering, March, 2020.

[16]

SISTU G, LEANG I, YOGAMANI S. Real-time joint object detection and semantic segmentation network for automated driving [J]. 2019.

[17]

SENER O, KOLTUN V. Multi-task learning as multi-objective optimization [J]. Advances in neural Information Processing Systems, 2018, 31.

[18]

STANDLEY T, ZAMIR A, CHEN D, et al. Which tasks should be learned together in multi-task learning? [C]//International conference on machine learning. PMLR, 2020: 9120-9132.

[19]

WU D, LIAO M W, ZHANG W T, et al. Correction to: YOLOP: You only look once for panoptic driving perception [J]. Machine Intelligence Research, 2023, 20(6): 952-952.

[20]

LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017(99): 2999-3007.

[21]

CRAWSHAW M. Multi-task learning with deep neural networks: A survey [J]. arXiv preprint arXiv: 2009.09796, 2020.

[22]

LIU S, JOHNS E, DAVISON A J. End-to-end multi-task learning with attention [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 1871-1880.

[23]

ZAMIR A R, SAX A, SHEN W, et al. Taskonomy: Disentangling task transfer learning [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3712-3722.

[24]

VANDENHENDE S, GEORGOULIS S, VAN GANSBEKE W, et al. Multi-task learning for dense prediction tasks: A survey [J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 2021, 44(7): 3614-3633.

[25]

JOCHER G, CHAURASIA A, STOKEN A, et al. Ultralytics/yolov5: v7.0-YOLOv5 SOTA real-time instance segmentation [J]. Zenodo, 2022.

[26]

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection [J]. arXiv preprint arXiv: 2004.10934, 2020.

[27]

LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.

[28]

LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8759-8768.

[29]

GOYAL P, DOLLÁR P, GIRSHICK R, et al. Accurate, large minibatch sgd: Training imagenet in 1 hour [J]. arXiv preprint arXiv: 1706.02677, 2017.

[30]

WEI L, DRAGOMIR A, DUMITRU E, et al. SSD: Single shot multibox detector [J]. Springer, Cham, 2016.

[31]

VU D, NGO B, PHAN H. HybridNets: End-to-end perception network [J]. 2022.

2025年第6卷第2期

预览PDF | 下载PDF

引用本文

BibTeX

文章信息

doi: 10.12398/j.issn.2096-7217.2025.02.003

接收时间：2025-04-10
首发时间：2026-11-05
出版时间：2025-05-15

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-04-10
修回日期：2025-05-10

基金

National Key Research and Development Program of China(2022YFB4702202)

国家重点研发计划项目(2022YFB4702202)

Integrated Pilot Project for Agricultural Machinery Research, Development, Manufacturing, Promotion and Application of Jiangsu Provincial Department of Agriculture and Rural Affairs(JSYTH07)

江苏省农业农村厅农机研发制造推广应用一体化试点项目(JSYTH07)

作者信息

^1.苏州大学机电工程学院，江苏苏州，215137

^2.江苏省具身智能机器人技术重点实验室，江苏苏州，215137

^3.苏州漕阳生态农业发展有限公司，江苏苏州，215143

^4.农业农村部南京农业机械化研究所，江苏南京，210014

通讯作者:

^* 王蓬勃，男，1984年生，安徽阜阳人，博士，副教授；研究方向为农业机器人、农业人工智能。E-mail：pbwang@suda.edu.cn

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/znhnyzbxb/CN/10.12398/j.issn.2096-7217.2025.02.003

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

BibTeX
EndNote
RefWorks
TxT