To solve the problem of stable information transmission for unmanned systems in complex electromagnetic environments, the information elastic adaptation method for unmanned systems based on communication quality assessment is proposed. Signal strength, bit error rate, and signal-to-noise ratio at the communication link layer are selected as characteristic parameters for communication quality assessment. Long Short-Term Memory ( LSTM) network is served as the signal prediction model to estimate future signal parameters, while a Support Vector Regression (SVR) model is employed to evaluate real-time communication quality. Based on the communication quality level evaluation model, the communication quality evaluation results are obtained; corresponding level of content is transmitted according to the communication quality level. Simulations using real-world data and field tests demonstrate that the proposed method ensures reliable information transmission for unmanned systems in highly dynamic and contested electromagnetic environments.

To address the inadequacy of multimodal data fusion and complexities in dynamic constraint optimization for satellite mission requirement decision-making, an intelligent decision model is designed to enhance automation and accuracy. The proposed Retrieval-Augmented Generation (RAG)-based optimization model for satellite mission planning comprises: ① An input layer receiving multimodal data such as user requirement texts and geospatial coordinates, etc. ; ② A processing layer integrating Transformer-architecture Large Language Model ( LLM) with vector databases to enable semantic retrieval and knowledge augmentation; ③ A constraint verification module in the output layer generating feasible solutions; ④ A feedback layer dynamically updating the knowledge base. Experimental validation demonstrates 90% decision accuracy—achieving 20% and 9.8% absolute accuracy improvements over conventional Rule-Based Expert Systems ( RBES) and Machine Learning Models ( MLM ), respectively. The model significantly enhances adaptability in satellite mission decision-making, enables efficient resource allocation under dynamic constraints, and exhibits substantial engineering applicability.

In traffic surveillance systems, radar-camera devices are used to collaboratively perceive and monitor the roadside environment. Due to the principles of perspective imaging, the greater the distance to a target, the smaller its corresponding pixel area in the image. Furthermore, the bounding boxes generated by visual detection exhibit significant jitter. If calibration errors or visual occlusion exist, or if the detection boxes shake, a significant error will be introduced when the target' s position is mapped from the image coordinate system to the radar coordinate system, affecting tracking accuracy. This is especially true for collaborative target sensing and tracking with multiple sensors, which further increases the difficulty. To address these challenges, a multi-sensor, multi-target collaborative perception and tracking method is proposed, leveraging a two-stage matching strategy and an adaptive Kalman filter. This method improves association precision by adding a secondary matching strategy of Perspective View (PV) plane after the Bird's Eye View (BEV) plane is associated with the data of frame before and after. This effectively solves the problem of low tracking accuracy for distant targets caused by significant mapping errors. Based on the relationship model between image points and range-position jitter, an adaptive multi-sensor multi-target tracking method is proposed. By using the relationship model to update the parameters of the Kalman filter, and adaptively selecting the appropriate observation matrix and measurement covariance matrix according to the target sensor data source, the position and velocity parameters of the target are estimated. This effectively improves the real-time prediction accuracy of the target' s spatial position and velocity, and further enhances the accuracy of target association in the BEV plane. Experimental results show that the proposed method improves the Multiple Object Tracking Accuracy ( MOTA) index by 16.3% compared to the method without the two-stage matching strategy and only using the ordinary Kalman filter, significantly improving the accuracy of target perception and tracking in traffic scenes using millimeter-wave radar and vision integrated systems.

A ship infrared image target detection algorithm based on YOLO11n, named AGT-YOLO, is proposed to address the issues of low model accuracy and recall rate, difficulties in identifying small targets, and multi-scale recognition challenges under complex sea conditions. By introducing an improved GhostHGNetv2 network, the background discrimination capability is enhanced; the designed ASFP2 optimized neck network improves detection capabilities for low-resolution images and very small targets; the proposed Tack Adaptive Alignment Detection Head ( TAADH ) replaces the original detection head, enhancing localization and classification performance;meanwhile, the AFGCAttention mechanism is integrated to improve global information processing capability and the model's generalization ability. Experimental results show that compared to the baseline model YOLO11n, AGT-YOLO achieves a 4.4% increase in recall rate and a 3.1% increase in mean average precision at IoU=0.5 ( mAP@ 50), demonstrating strong multi-scale recognition capability and robustness in complex environments.

The application value of Brain-Computer Interface (BCI) and human-machine integration technology in the fields of UAV control and countermeasure equipment operation is explored, the problems faced by these technologies are analyzed, and targeted solutions are proposed to promote their rational application in the development of the low-altitude economy and security protection. By analyzing the role of BCI technology in improving UAV control efficiency and enhancing the accuracy of countermeasure equipment operation, and combining the new application scenarios that BCI technology shapes for the low-altitude economy and the new form of low-altitude security protection it creates, the problems faced by these technologies are sorted out, such as inherent defects of human-machine integration technology, information security risks, and their impacts on low-altitude security, and corresponding countermeasures are further put forward. BCI technology plays a significant role in the fields of UAV control and countermeasure equipment operation: it can improve UAV control efficiency and enhance the accuracy of countermeasure equipment operation. Based on BCI and human-machine integration technology, new application scenarios for the low-altitude economy have been shaped, and a new form of low-altitude security protection has been created.

To solve the problems of tracking and positioning of airborne early warning aircraft and other long-range targets，a high-precision passive positioning strategy based on the collaborative networking of UAVs and passive radar is proposed. By analyzing the impact of the layout of multi-station passive radar on positioning accuracy，a layout strategy that can improve positioning accuracy and reduce layout costs is designed. Time Difference of Arrival (TDOA) positioning method is applied in the study，and on this basis，the Geometric Dilution of Precision ( GDOP) for multiple stations is analyzed to evaluate the impact of the layout form on positioning accuracy. A collaborative strategy is proposed that，when the initial direction of the target is unknown，first uses a star-shaped layout for initial positioning and then switches to an inverted triangular layout for high-precision secondary positioning. The optimal secondary stations are selected using the “virtual structure method”and the flight trajectory of the UAV is optimized using an improved Particle Swarm Optimization ( PSO) algorithm to achieve high-precision layout. Simulation results show that this strategy can significantly improve positioning accuracy. Compared with traditional passive radar systems，positioning error is significantly reduced，and system response speed is faster. The research results have certain application value in practice.

The BeiDou-3 Global Navigation Satellite System ( BDS-3) can provide data of six frequencies at present, which provides more choices for Multi-frequency Carrier Ambiguity Resolution (MCAR). Focusing on BDS-3, the basic method of Geometry and Ionosphere Free (GIF) model in MCAR is comprehensively studied, including the application of three-frequency GIF model in ambiguity resolution. Based on the theory of three-frequency linear combinations, the basic mathematical model under three-frequency is given. The optimal frequency combination for ambiguity resolution using GIF model is discussed under the possibility of 20 combinations of any three of the six frequencies. Meanwhile, the optimal linear combination of each frequency combination is also systematically discussed. In addition, the high-quality linear combinations for single-epoch ambiguity resolution using GIF model are also analyzed. The experiment is carried out by using the real BDS-3 six-frequency data. Through theoretical analysis and practical demonstration, the results show that when using the GIF model for ambiguity resolution, the optimal frequency combination is (B1C, B3I, B2a). In this method, if the sum of the coefficients of two fixed Extra Wide Lane /Wide Lane (EWL/WL) combinations equals zero, the standard deviation of the ambiguity for the third Narrow Lane (NL) combination is theoretically dependent solely on the frequency characteristics. However, due to the influence of unmodeled errors, the actual results may deviate from theoretical expectations. The GIF model effectively eliminates ionospheric delay effects and avoids Geometry Base ( GB) errors, demonstrating significant advantages. The ambiguity resolution based on GIF model exhibits strong potential particularly in ionosphere-active environments and medium-to-long baseline scenarios.

An algorithm for weed recognition in beet fields based on improved YOLOv11 model is proposed to address the problems of low efficiency, low accuracy, and missed detection of small targets in complex real-world scenarios. The PoolFormer module and AKConv module are introduced into the backbone network to enhance the model's ability to capture global semantic information to improve detection accuracy, enhancing the detection performance in low resolution images and small objects. The AKConv module improves the feature extraction ability of the model for beets and weeds with irregular growth patterns by dynamically adjusting the convolution kernel parameters and shapes, while the PoolFormer module can effectively segment the edge features of beets and weeds that cover each other. Secondly, the High-level Screening Feature Pyramid Network (HS-FPN) module is added to the head network to enhance the efficiency of multi-scale fusion and improve the feature extraction efficiency and speed of beets and weeds during the seedling stage. Through experiments, it is found that the improved YOLOv11 model achieves increases of 6.9%, 7.8%, 7.9%, and 7.8% in precision, recall, mAP@0.5 and mAP@0.5: 0.95, respectively, compared to the original model. The results show that this algorithm has achieved significant improvement in weed recognition in beet fields, providing a more feasible solution for detecting weeds in beet fields in complex scenarios.

Vision-Language-Action (VLA) models are a core technology for achieving general embodied artificial intelligence, aiming to integrate visual perception, language understanding, and action decision-making within a unified end-to-end framework. The current research status and development trajectory of VLA models are comprehensively and systematically reviewed. The theoretical origins of VLA models are traced, and the paradigm shift from modular designs to unified architectures is clarified. Along the evolutionary path of VLA, representative works such as SpatialVLA, TLA, and GR00T N1 are presented with a focus on multimodal fusion and cognitive hierarchies. A detailed taxonomy of VLA models is constructed from two key dimensions-macro architecture and system hierarchy. Key technologies and design principles are deeply analyzed, ranging from pioneering works such as RT-1, to models introducing large-scale knowledge transfer such as RT-2, OpenVLA, and ECOT, and further to cutting-edge dual-system architectures such as Helix, OpenHelix, DexVLA, and DexGraspVLA. Mainstream simulation environments, core datasets, and benchmarks supporting VLA research are systematically integrated and reviewed. The application status and prospects of VLA models in robotic manipulation, autonomous navigation, and industrial automation are explored. Core challenges in current VLA research are analyzed, including generalization and data efficiency, long-horizon task planning, and real-time responsiveness. Future research directions are discussed, including integration with world models and enhancement of data efficiency.

Target detection in autonomous driving scenarios faces challenges such as complex environmental interference, multi-scale target distribution and target occlusion, and existing algorithms are still deficient in feature fusion capability, detail characterization accuracy and localization regression performance. To this end, an improved YOLOv8 detection algorithm, DMP-YOLO, is proposed. The original neck structure is optimized using Multi-Branch Auxiliary Feature Pyramid Network (MAFPN) to enhance the multi-scale feature fusion capability in complex traffic scenarios; C2f_DEConv is proposed in backbone network module, which replaces the standard convolution with Detail-Enhanced Convolution (DEConv) to significantly improve the detail capturing ability of small-scale vehicles and occluded targets through high-frequency feature preservation and local texture enhancement; the Powerful Intersection over Union version 2 (PIoUv2) loss function is introduced to optimize the improved bounding-box loss, which improves the regression accuracy of the target bounding-box through the optimization of dynamic scale-sensitive factors and geometric constraints. Experiments on the KITTI dataset demonstrate that DMP-YOLO achieves significant improvements across all key performance metrics, with mAP@0.5 reaching 89.0% (2.6% improvement compared with the baseline YOLOv8) as well as 2.9% improvement for mAP@0.5: 0.95, which provides an effective solution for high-precision real-time detection in autonomous driving scenarios.