The research of Cooperative Operation System-of-Systems (COSoS) for Manned Aerial Vehicles (MAV) and Unmanned Aerial Vehicles (UAV) has garnered significant attention recently due to its potential to enhance situational awareness, expand mission capabilities, and reduce pilot risk. A critical aspect of this research is the modeling and effectiveness evaluation of MAV/UAV COSoS. This paper presents a review of current research on MAV/UAV COSoS modeling and evaluation methods. Firstly, the definition of MAV/UAV COSoS is clarified, and its composition is described. Secondly, the latest research progress on MAV/UAV COSoS modeling methods based on standard framework-based modeling and complex network-based modeling is presented. Differences between the two types of methods in characterizing MAV/UAV COSoS are then summarized. Next, this paper introduces the research progress on MAV/UAV COSoS effectiveness evaluation methods and concludes by summarizing the advantages and disadvantages of evaluation methods and evaluation index systems in MAV/UAV COSoS. Finally, future trends and possible research directions are suggested.

Maritime object detection is essential for resource monitoring, maritime defense, and public safety, yet detecting diverse targets beyond ships remains challenging. This paper presents YOLO-SEA, an efficient detection framework based on the enhanced YOLOv8 architecture. The model incorporates the SESA (SimAM-Enhanced SENetV2 Attention) module, which integrates the channel-adaptive weight adjustment of SENetV2 with the parameter-free spatial-channel modeling of SimAM to enhance feature representation. An improved BiFPN (Bidirectional Feature Pyramid Network) structure enhances multi-scale fusion, particularly for small object detection. In the post-processing stage, Soft-NMS (Soft Non-Maximum Suppression) replaces traditional NMS to reduce false suppression in dense scenes. YOLO-SEA detects eight maritime object types. Experiments show it achieves a 5.8% improvement in mAP@0.5 and 7.2% improvement in mAP@0.5:0.95 over the baseline, demonstrating enhanced accuracy and robustness in complex marine environments.

The architecture of the Manned/Unmanned Aerial Vehicle Collaborative Operation System (MAV/UAV COS) is crucial for improving combat effectiveness and resource utilization efficiency. Optimizing this architecture involves managing complex, interdependent components, which presents a constrained multi-objective optimization challenge. Initially, the elements of the MAV/UAV COS architecture were analyzed and formally expressed, transforming the architecture optimization problem into a multi-objective optimization problem, with the objectives of maximizing total system effectiveness, command-and-control performance, and system execution performance. Constraints were formulated based on mission and payload information. Subsequently, a Quantum Non-Dominated Sorting Genetic Algorithm based on Preference Guidance (PGQNSGA-II) was developed, incorporating an adaptive quantum gate mechanism based on preference information to enhance chromosome updating, ensuring that the probability amplitude of quantum bits aligns more closely with the optimal chromosome. The simulation results demonstrate that the proposed PGQNSGA-II algorithm significantly enhances the global search capability and efficiency compared to traditional quantum genetic algorithms, making it well-suited for optimizing MAV/UAV COS architectures.

Non-cooperative spatial target detection plays a vital role in enabling autonomous on-orbit servicing and maintaining space situational awareness (SSA). However, due to the limited computational resources of onboard embedded systems and the complexity of spaceborne imaging environments, where spacecraft images often contain small targets that are easily obscured by background noise and characterized by low local information entropy, many existing object detection frameworks struggle to achieve high accuracy with low computational cost. To address this challenge, we propose YOLO-GRBI, an enhanced detection network designed to balance accuracy and efficiency. A reparameterized ELAN backbone is adopted to improve feature reuse and facilitate gradient propagation. The BiFormer and C2f-iAFF modules are introduced to enhance attention to salient targets, reducing false positives and false negatives. GSConv and VoV-GSCSP modules are integrated into the neck to reduce convolution operations and computational redundancy while preserving information entropy. YOLO-GRBI employs the focal loss for classification and confidence prediction to address class imbalance. Experiments on a self-constructed spacecraft dataset show that YOLO-GRBI outperforms the baseline YOLOv8n, achieving a 4.9% increase in mAP@0.5 and a 6.0% boost in mAP@0.5:0.95, while further reducing model complexity and inference latency.

The collaborative operation system (COS) of manned/unmanned aerial vehicle (MAV/UAV) has garnered significant attention and stands as a pivotal paradigm for future warfare. Evaluation of its effectiveness is indispensable in its development. This paper aims to propose an Availability-Dependability-Capability (ADC) effectiveness evaluation method for MAV/UAV COS based on the Absorbing Markov Chain (AMC) and Human Factors (HF). In the development of MAV/UAV COS, HF are of paramount importance. This paper first establishes a HF model for the system, considering operator reliability and capability-related factors. Building on the traditional ADC model, which considers physical level elements, cognitive and psychological level elements have been added. Next, the paper establishes an ADC framework by mapping the collaborative operation situational change process to the Absorbing Markov Process, thus enhancing the applicability of the ADC model to COS and further enhancing the accuracy of effectiveness evaluation. Experimental results demonstrate consistency between the evaluation outcomes and the trends in operator reliability states. The effectiveness evaluation results of the AMC-HFADC method are more accurate. Compared to traditional ADC models, the method offers a more scientifically sound evaluation process, providing better boundary conditions for MAV/UAV COS in specific scenarios.