This paper provides a comprehensive review of the task planning methods for manned/unmanned system cooperative combat. It begins by introducing the research background and analyzing the problem from two aspects of the human-machine relationship within manned/unmanned systems and the task planning process. This analysis leads to the identification of five key technical areas: task understanding, task decomposition, task allocation, course of action generation, and plan evaluation. Each of these areas is then comprehensively reviewed, with a focus on the relevant research. Finally, the paper summarizes and analyzes the current research status of task planning for manned/unmanned systems cooperative combat as a whole, and provides the prospects for the future of this field.

When using Unscented Kalman Filter (UKF) algorithm for state estimation, the abnormal system noise covariance matrix may affect the filtering performance. To address the problem, a method utilizing the Improved Artificial Bee Colony Optimized UKF (IABC-UKF) algorithm is proposed. Firstly, IABC is introduced into the UKF algorithm to optimize the selection of the system noise covariance matrix, thus to achieve adaptive adjustment of the system noise covariance matrix and improve estimation accuracy. Secondly, a Circle chaos initialization strategy is applied to the traditional ABC algorithm to increase the diversity of the initial population of artificial bee colony. Additionally, a preference random walk strategy is employed to balance the algorithm's exploitation and exploration capabilities, enhancing algorithm stability. Finally, a dynamic perturbation factor strategy is used to enhance the algorithm's ability to find the optimal solution in the later stages, improving convergence speed and further optimizing algorithm performance. Experimental results demonstrate that compared with the ABC algorithm, IABC algorithm has a significant improvement in optimization performance. Furthermore, a comparison between the UKF algorithm and the IABC-UKF algorithm confirms the feasibility of the IABC-UKF algorithm. With a root mean square error in position not exceeding 1.4 meters, IABC-UKF algorithm exhibits good filtering performance with low error fluctuations, which can effectively enhance the estimation accuracy.

In response to the issues of drifting and tracking failures encountered in the Visual-Inertial SLAM (VIO-SLAM) algorithm under complex lighting conditions, an improved algorithm is proposed. The algorithm, called PVIO-SLAM, performs illumination discrimination on images and applies adaptive logarithmic correction and CLAHE to different illumination. Then, the adaptive weighted fusion strategy proposed in this paper is used to fuse the pre-processed images, the pre-integral is used to reduce the matching range and accelerate the feature point tracking and matching, and the loopback check is introduced to improve the robustness of the algorithm. Experimental results on a public dataset demonstrate that, compared with the original algorithm, when loopback check is not used, the proposed algorithm achieves an average reduction of 35.75% in RMSE, which is further reduced by 14.96% when enabling loopback check. Experimental results in real-world scenarios indicate that the proposed algorithm yields motion trajectories that are closer to the ground truth. In summary, the proposed algorithm effectively improves the accuracy and robustness of VIO-SLAM under complex lighting conditions.

Aiming at the problems of low convergence accuracy and local optimization of heuristic algorithm in Unmanned Aerial Vehicle (UAV) path planning, an Adaptive Osprey Optimization Algorithm (AOOA) is proposed. Firstly, Bernoulli chaotic mapping is used to improve the population diversity effectively. Secondly, adaptive cosine factor is introduced to balance the global search ability and local development ability, and in combination with Levy flight strategy, the step size is adjusted adaptively to help the individual osprey better jump out of the local optimal. Then, the refraction reverse learning strategy is used to improve the quality of the global optimal solution, and the convergence accuracy and speed are improved to a certain extent. After that, the performance of the algorithm is compared with that of other 5 algorithms in 15 CEC2005 test functions, and the results show that the algorithm has excellent performance in convergence accuracy and stability. Finally, it is transplanted to the UAV path planning problem and tested under the terrain obstacle models with 6, 9 and 12 peaks. The simulation results show that, compared with other algorithms, AOOA has lower average cost, lower standard deviation, and shorter and more stable path in different terrain scenarios.

The electromagnetic environment of modern battlefield is becoming more and more complex, and there are many kinds of radar emitter. The traditional radar emitter recognition method in closed set environment has low identification accuracy and poor robustness when applied to open set environment. In order to effectively solve the problem of individual emitter open set identification and improve the accuracy of individual emitter identification, an open set identification method of radar emitter based on EfficientNet-WGANomaly is proposed. Firstly, the Short-Time Fourier Transform (STFT) is used to convert the time-frequency feature of the radar emitter signal, and the one-dimensional signal data is converted into two-dimensional image data. The EfficientNet-WGANomaly model is used to perform feature reconstruction and image reconstruction of the converted time-frequency feature. Since the feature and image of unknown signals change greatly after reconstruction, the known signals and unknown signals are screened by using the reconstruction difference of the two parts, and the known signals are classified and identified. Simulation results show that the proposed method can effectively solve the problem of specific radar emitter identification in open set environment.

In a multi-sensor collaborative tracking system, such risk factors as multi-sensor radiation and target misidentification may lead to problems of increased probability of system being attacked, decreased tracking accuracy, and decreased system safety. Therefore, this paper proposes a multi-sensor management method based on bidirectional risk, which is used to solve multi-sensor allocation under multiple kinds of risks. First, the radiation risk of our sensors and the misidentification risk of new enemy targets are integrated, and a bidirectional risk model with adaptive risk weights is built by using the change of range between the target and the sensors. Second, the optimization problem of multi-sensor allocation is proposed, which includes target tracking accuracy function and the bidirectional risk constraints, and the sensor resources are reasonably allocated. Simulation results show that the proposed method is feasible, and can improve the accuracy and safety of multi-sensor tracking system.

In view of the problems of small size and blurry appearance of images shot from the perspective of UAV, and motion of the UAV platform itself, the detecting and tracking of moving objects based on UAV images is still very challenging. A moving object detecting and tracking algorithm based on the improved LK optical flow method is proposed, and the Kalman filter algorithm is used for object tracking. In order to solve the problem that the traditional LK optical flow method is not effective in the dynamic environment, the semantic segmentation thread is introduced to screen the dynamic points and static points, the motion compensation of the UAV is completed by solving the homography matrix through the static points, and the optical flow value of the dynamic points are calculated to obtain the optical flow points for reducing the mismatch rate. Finally, the complete moving object is obtained through the clustering algorithm and morphological algorithm, and the proposed re-identification module is introduced into the Kalman filter algorithm to realize object tracking. The experimental results verify that the moving object detecting and tracking algorithm designed here can accurately extract the moving object in real time from the perspective of the UAV, and track it continuously and stably.

Aiming at the issues of local optima trapping, inadequate global search capability, and low convergence accuracy in traditional intelligent bionic algorithms when solving three-dimensional path planning problems of Unmanned Aerial Vehicles (UAVs), a novel UAV path planning method based on improved Dung Beetle Optimization (DBO) is proposed. Firstly, a three-dimensional model of mountainous terrain is established using a mathematical model. And with consideration of the objective function and constraints of UAVs, the experimental environment is more consistent with actual scenarios. Secondly, a segmented linear chaotic mapping is introduced to initialize the population of the DBO, enhancing its global search capability. An adaptive nonlinear decreasing model is employed to dynamically adjust the number of rolling-ball dung beetles in the early and late stages of the algorithm, thereby improving the convergence speed. Finally, the spiral search strategy of the Whale Optimization Algorithm (WOA) is incorporated into the position updates of breeding and foraging dung beetles to strengthen the local search capability of the algorithm and improve convergence accuracy. The improved DBO is compared with other intelligent bionic algorithms for 3D path planning of UAV in simulation experiments. The results demonstrate that the improved algorithm achieves better performance in terms of path length, convergence speed with smoother paths, which verifies its effectiveness.

The commercialization and popularization of UAVs have brought great efficiency improvement to many industries, while the security threat posed by UAVs is also increasing rapidly. Therefore, countermeasure technologies such as UAV detection and strike technologies have emerged correspondingly. Among the UAV countermeasures, navigation spoofing has been widely researched for its advantages such as great concealment, soft-killing, high effectiveness-cost ratio, and target dynamic controllability. This paper illustrates the principle of UAV navigation spoofing technology, proposes a novel classification framework of spoofing technology according to the characteristics of spoofed UAV trajectory. Then, systematical analysis is made on the current status of the related research, the problems existed within each spoofing technology category under the new classification framework. The development trend of UAV navigation spoofing technology is predicted in the end.

With the expanding applications of mobile robots, precise positioning and orientation have become key techniques for achieving autonomous navigation and control. However, due to the complexity of the environment and sensor errors and other factors, there are certain biases in the estimation of the posture of mobile robots. For this reason, a digital twin system is built for mobile robots based on the ROS, and a virtual-real positioning error compensation method is proposed under this system. An Adaptive Genetic Algorithm-based Predictive Optimization Controller (AGA-POC) is designed to drive the controlled models by issuing control commands to compensate for the positioning error existed in the virtual-real mapping process. The experimental results show that compared with Model Predictive Control (MPC) compensation, the positioning error and trajectory deviation of the mobile robots are reduced by 60.43% and 35.66% respectively, the trajectory similarity and controller response rate are improved by 69.28% and 71.14% respectively, which verifies the feasibility and validity of the compensation strategy in terms of positioning accuracy, trajectory accuracy and controller response rate.

The real-time detection of aerial refueling drogue is an important prerequisite for the realization of autonomous aerial refueling. Since the existing object detection algorithms in aerial refueling drogue detection is susceptible to environmental interferences and may result in insufficient accuracy, a real-time detection algorithm for aerial refueling drogue based on the Transformer feature pyramid is proposed. Firstly, a new pooling attention-based Transformer feature pyramid structure TPN is proposed for backbone feature fusion to achieve more efficient feature map enhancement. Then, linear attention is used to reduce complexity of the attention mechanism in TPN, and the lightweight detection model DNet-LinTPN is proposed to reduce the memory consumption by 80%. The experimental results on the self-created air refueling drogue dataset show that the TPN-based model outperforms YOLOv7 in terms of accuracy, speed and model size under the same conditions. The lightweight detection model of DNet-LinTPN achieves an accuracy of 93.8%, which is a 9.4 percentage point improvement over YOLOv7-tiny, with a 67.2% reduction in the amount of parameters and a 45.2% reduction in the amount of operations, and the robustness is obviously improved.

For small target detection in aerial images of UAVs, due to limitations such as low pixel values, lack of rich features, difficulty in feature extraction, and susceptibility to environmental interference, it is easy to lead to missed detections, low accuracy, and excessive network parameter quantities. To solve the problems, a small target detection model for UAVs based on improved YOLOv5s network is proposed. The YOLOv5s network structure is improved by reducing the network structure and parameter quantity without adding small object detection heads, making the model lighter. A pyramid pooling module, ASPPF, is proposed, which adds dilated convolution to the SPPF module of the YOLOv5s network to enhance the spatial invariance of feature information and enhance the spatial invariance of feature information. The perception ability of the network towards small targets is improved by adopting a Cross Layer Upsampling (CLAU) attention module. After the upsampling process, the low-resolution deep features are fused with the high-resolution shallow features to improve the detection efficiency of small target images. The EIoU loss function is used to replace the original CIoU loss function to improve the convergence speed of training. Validation on the VisDrone2019 dataset shows that: 1) The improved model performs well in mAP@0.5 and mAP@0.5∶0.95 with values of 41.2% and 23.4% respectively, which are 7.2 and 4.7 percentage points higher than that of the original model; and 2) The number of parameters is only 49% of the original model.

To solve the problem of low scheduling efficiency and resource utilization rate of large-scale multithreaded testing tasks in automatic test of avionic equipment, a load balancing screening mechanism is designed, a parallel testing static resource scheduling model is established, and an improved Particle Swarm Optimization (PSO) task scheduling algorithm based on particle encoding and decoding is proposed. Bidirectional learning or gravitational/repulsive force mechanism is selected through chaotic initialization sequence and decision weight selection, thus the efficiency and accuracy of PSO is improved. On this basis, in response to the rescheduling problem in automatic testing, different objective functions are established based on the urgency of the test piece to complete the test of urgent parts during the testing process, and thus the dynamic planning ability of the scheduling method is improved. Simulation experiments have verified that the scheduling method can effectively improve the scheduling efficiency and resource utilization rate of parallel testing tasks.

To effectively extract the spatial spectral structural features of hyperspectral remote sensing images, enhance feature discrimination and improve classification accuracy, a classification method for hyperspectral remote sensing images is proposed based on local ternary pattern encoded fractional order Gabor. Firstly, effective extraction of local features is achieved using fractional order 3D Gabor filters. Secondly, local ternary mode encoding is applied to Gabor phase features to improve their discriminability. Then, Gabor phase features are classified using a random forest algorithm to obtain confidence cubes. Finally, by fusing multiple sets of Gabor based confidence cubes, the textural features with complementarity and strong expressivity are extracted. Three training samples are selected for validation on the Indian Pines, Salinas, and Trento datasets, and the overall classification accuracy reaches 63.50%, 81.78%, and 86.89%, respectively. The experimental results verifies that the proposed method has better classification performance.

In addressing the challenge of UAV target search under uncertain prior information conditions and with consideration of sensor detection probability and false alarm probability, a probability-adaptive updating strategy for target search is devised. Firstly, a probability map of the uncertain prior environment is established by using the Beta distribution. Subsequently, an adaptive target search probability updating strategy is proposed, enabling the UAV to dynamically adjust detection frequencies based on the probability information map. Furthermore, within the probability updating strategy, a rejection probability correction factor is introduced to dynamically regulate the probability change quantity based on map probability discrepancies, thereby mitigating potential false positives and false negatives in the search task. Finally, numerical simulation experiments validate that the proposed target search adaptive updating strategy can decrease UAV false detection probability effectively without compromising search efficiency.

The angle of attack and sideslip angle are the key parameters that affect the safety of flight control system. However, it is difficult for the atmospheric data system to accurately measure the air flow angles in severe weather or highly maneuvering flight, and flight safety issue may occur in the case of fault isolation failure. Based on this, an Adaptive Unscented Kalman Filter (AUKF) based flow angle fusion method is proposed. The filtering model is constructed by the information of inertial navigation system and aircraft dynamics model. At the same time, the adaptive filtering idea is applied to AUKF, and the Chi-square test and adaptive fading matrix are constructed by using the observed residual sequence, and the high precision output of flow angle under dynamic flight and fault conditions is realized. The simulation results show that the performance of this algorithm is better than that of the traditional extended Kalman filter algorithm and it has great engineering application value.