In this paper, a novel infrared maritime small target detection method, called local dissimilarity measure with anti interference based on global graph clustering (LDMGGC), is proposed. The Wasserstein distance is introduced to calculate the dissimilarity of gray level distribution between a central region and its neighborhoods. These dissimilarities construct the feature of a region. With this feature, detection for recalling all suspected targets is achieved. As the maritime interferences among suspected targets are able to be clustered, relaxing mutual k nearest neighbor graph is introduced in global graph clustering for filtering interferences. With this method, real targets are detected and maritime interferences are filtered out. Experiments are conducted on three maritime datasets and a non-maritime dataset for comparison. On three datasets, the proposed method achieves the best Receiver Operating Characteristic curves and Area Under Curve (0.99529, 0.99945, 0.99573, and 0.9906) values, meaning that the proposed method has high detection probability and low false-alarm ratio. Target Hit Rate (98.04%, 97.96%, 100%, and 99.24%) and Intersection of Union (0.8170, 0.7542, 0.5824, 0.7707) on four datasets of the proposed method show it has a strong ability to suppress the interferences

Aiming at the non-cognitive environment such as dynamic and static obstacles and external interference, a real-time collision avoidance strategy based on flexible steering method under the framework of deep reinforcement learning (RL) is proposed. The strategy extracts effective state features required for obstacle avoidance by developing an efficient multibeam sonar detection information coding module, and integrates the safety and energy cost as the induced factors for online control decisions. Meanwhile, a novel sampling priority scheme is introduced to assist UUV to obtain a better obstacle avoidance capability in response to the problems of low input state coupling and sample efficiency in the training environment. In order to achieve the application of the control strategy obtained from simulation training to real UUV, a disturbance estimation and cancellation method based on dynamic compensation is designed. Finally, the effectiveness of the proposed strategy is confirmed by experiments in different complex obstacle environments.

This paper focuses on the reachable set problem for impulse switched singular (ISS) systems with mixed time‐varying delays via the Lyapunov theory. To solve the state boundary of system, a real‐bounded lemma is developed by analyzing the impulse switching point under bounded disturbance input and initial function. Based on real‐bounded lemma and integral inequality technology, a sufficient condition for reachable set of ISS system is established in the form of linear matrix inequalities (LMIs) to ensure that the reachable state of system is limited to a closed bounded set. Simulation results are given to verify the validity of the obtained theoretical results for the reachable state criterion.

Due to its highly autonomy, the strapdown inertial navigation system (SINS) is widely used in unmanned underwater vehicles (UUV) navigation. Initial alignment is crucial because the initial alignment results will be used as the initial SINS value, which might affect the subsequent SINS results. Due to the rapid convergence of Earth meridians, there is a calculation overflow in conventional initial alignment algorithms, making conventional initial algorithms are invalid for polar UUV navigation. To overcome these problems, a polar initial alignment algorithm for UUV is proposed in this paper, which consists of coarse and fine alignment algorithms. Based on the principle of the conical slow drift of gravity, the coarse alignment algorithm is derived under the grid frame. By choosing the velocity and attitude as the measurement, the fine alignment with the Kalman filter (KF) is derived under the grid frame. Simulation and experiment are realized among polar, conventional and transversal initial alignment algorithms for polar UUV navigation. Results demonstrate that the proposed polar initial alignment algorithm can complete the initial alignment of UUV in the polar region rapidly and accurately.