It is an important and difficult problem to control the cooperative operation of the ground unmanned system formation in the communication restricted environment of land battlefield. In this paper, the problem of autonomous navigation control of tracked unmanned vehicle formation in communication restricted environment is studied, and the Visual Limiting-Multi-agent Deep Deterministic Policy Gradient (VL-MADDPG) algorithm is proposed. First, in order to reduce the influence of large policy space and non-stationary environment on algorithm convergence, a visual limiting mechanism is proposed. By focusing the dependent information of the algorithm decision within the visual boundary, the communication requirement is further reduced while the state space is compressed, and the learning efficiency of the algorithm is improved. Then, a non-sparse reward function with time series is constructed based on the tracked vehicle motion model, and the policy is further optimized on the basis of synthesizing continuous action information. Finally, the VL-MADDPG algorithm is proposed and embedded into the autonomous navigation control task of tracked unmanned vehicle formation, which is the first attempt of collaborative control of tracked vehicles by related algorithms. The experimental results show that the proposed algorithm has good convergence and scalability compared with other excellent algorithms, and can complete the autonomous navigation control task of the tracked unmanned vehicle formation in the communication restricted environment.

Unmanned helicopter (UH) is often utilized for raid missions because it can evade radar detection by flying at ultra-low altitudes. Path planning is the key technology to realizing the autonomous action of UH. On the one hand, the dynamically changing radar coverage area and the mountains in the low airspace environment will seriously affect the flight safety of UH. On the other hand, the huge state space of the three-dimensional (3D) environment will also make traditional algorithms difficult to converge. To address the above problems, a memory-enhanced dueling deep Q-network (ME-dueling DQN) algorithm was proposed. First, a comprehensive reward function was designed, which can guide the algorithm to converge quickly and effectively improve the sparse reward problem. Then, we introduced a dual memory pool structure and proposed a memory-enhanced mechanism, which can reduce invalid exploration, further improve the learning efficiency of the algorithm, and make the algorithm more stable. Finally, the path planning ability of the proposed algorithm in multiple experimental environments was verified. Experiments showed that the proposed algorithm has good environmental adaptability and can help UH to accurately identify dangerous areas and plan a safe and reliable flight path.

Unmanned helicopters (UH) can avoid radar detection by flying at ultra-low altitudes; thus, they have been widely used in the battlefield. The flight safety of UH is seriously affected by moving obstacles such as flocks of birds in low airspace. Therefore, an algorithm that can plan a safe path to UH is urgently needed. Due to the strong randomness of the movement of bird flocks, the existing path planning algorithms are incompetent for this task. To solve this problem, a state-coded deep Q-network (SC-DQN) algorithm with symmetric properties is proposed, which can effectively avoid randomly moving obstacles and plan a safe path for UH. First, a dynamic reward function is designed to give UH appropriate rewards in real time, so as to improve the sparse reward problem. Then, a state-coding scheme is proposed, which uses binary Boolean expression to encode the environment state to compress environment state space. The encoded state is used as the input to the deep learning network, which is an important improvement to the traditional algorithm. Experimental results show that the SC-DQN algorithm can help UH avoid the moving obstacles to unknown motion status in the environment safely and effectively and successfully complete the raid task.

Image registration is the base of subsequent image processing and has been widely utilized in computer vision. Aiming at the differences in the resolution, spectrum, and viewpoint of infrared and visible images, and in order to accurately register infrared and visible images, an automatic robust infrared and visible image registration algorithm, based on a deep convolutional network, was proposed. In order to precisely search and locate the feature points, a deep convolutional network is introduced, which solves the problem that a large number of feature points can still be extracted when the pixels of the infrared image are not clear. Then, in order to achieve accurate feature point matching, a rough-to-fine matching algorithm is designed. The rough matching is obtained by location orientation scale transform Euclidean distance, and then, the fine matching is performed based on the update global optimization, and finally, the image registration is realized. Experimental results show that the proposed algorithm has better robustness and accuracy than several advanced registration algorithms.

Infrared and visible image fusion combine data information from different sensors to achieve a richer description of the same scene. In order to highlight the salient features of the infrared image and the visible image in the fusion image and obtain a fusion image with good performance, an end-to-end infrared and visible image fusion algorithm is proposed in this paper. The contrast attention module and visible image cascade part are introduced in the generator, so that the fusion image can focus on the detail information in the visible image and the contrast information in the infrared image. And in order to retain more structural contour information in the original image, the contour loss is added to the content loss function. In addition, the contrast and detail information in infrared and visible images are balanced by two discriminators. And a goal-guided reward function is introduced into the discriminator, which further facilitates the generator to produce effective fused images. Finally, extensive fusion experiments on public datasets verify the advantages of the proposed algorithm compared with other classical algorithms, and ablation experiments demonstrate the effectiveness of the improved part of the algorithm.

Aiming at the problems of limited feature expression and underutilization of contextual information in the object detection task in low-light environments, a low-light object detection algorithm based on feature complementarity and multicontent aggregation (FCMA-Det) is proposed in this article. The algorithm is based on the FCOS framework and improves the model performance through a stepwise optimization strategy. First, the feature complementary module (FCM) is designed. By dynamically fusing the dual-domain features of the original low-light image and the augmented image, the feature discriminative property of the augmented domain is strengthened while retaining the detail information of the original domain, so as to solve the problem of insufficient single-domain feature expression capability. Second, a multicontent aggregation module (MAM) is constructed. Combining multiscale context fusion and adaptive sensory field adjustment mechanism, it accurately captures the local details of the object and long-range context dependencies, and effectively copes with the challenges of complex background interference and insufficient feature extraction. In addition, feature consistency loss and dynamic weight fusion loss function are introduced to further optimize cross-domain feature alignment and multibranch collaborative training. Experiments on low-light dataset such as Exclusively Dark (ExDark) and small-object mixed-light dataset such as tiny object detection in aerial images (AI-TOD) show that the mean average precision (mAP) metric of FCMA-Det is improved by 1.7% on average compared with the existing SOTA method, which verifies the robustness and generalization ability of the algorithm under extreme light conditions.