Coverage path planning (CPP) for target search by autonomous unmanned vehicle (AUV) involves two crucial aspects: (1) the sonar performance of the AUV is sensitive to ocean environment, such as changes in terrain; and (2) the ocean currents significantly influence AUV dynamics AUV dynamics. To address the CPP of multiple AUVs (multi-AUV) considering both sonar performance and ocean currents, we propose a new integrated algorithm based on the improved Dijkstra algorithm, Particle Swarm Optimization (PSO), and the ELKAI Solve. First, the necessary sampling points for the area coverage are identified based on the sonar detection range at different locations, which is calculated by combining the ocean acoustics model with the sonar equation. Second, an improved Dijkstra algorithm is presented to solve the adjacency matrix of the graph formed by all sampling points under the influence of ocean currents. Third, the PSO algorithm is utilized for task allocation, and the ELKAI solver determines the optimal path for each AUV. Finally, multi-AUV path planning is achieved through iterations of the PSO algorithm and the ELKAI solver. Simulation results demonstrate the outstanding performance and robustness of our integrated algorithm.

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of training data quickly, which are used to train the U-Net. The performance of AIS recovery of the U-Net is tested in range-dependent waveguides with nonlinear internal waves (NLIWs). Although the random mode-coupling matrix model is not an accurate physical model, the test results show that the U-Net successfully recovers AISs under different signal-to-noise ratios and different amplitudes and widths of NLIWs for different shapes.

Edge computing extends computational capabilities to the physical edge of the world, providing faster and more efficient responses to consumer devices such as smart home appliances, smartphones, and wearable devices. However, it raises a critical question: How can we efficiently manage time-sensitive and computationally intensive tasks to meet device performance needs? To address this, we propose a computational cost-driven strategy for computation offloading based on reinforcement learning for consumer devices. Firstly, we convert the problem of minimizing computational costs, including latency and energy consumption, into maximizing the cumulative rewards problem of consumer devices. Second, we design a task completion time estimation method to ensure a favorable user experience. Third, by comprehensively considering the status of the network, computational demands, and task completion times, we employ reinforcement learning techniques to determine the optimal task offload strategy for consumer devices by maximizing cumulative rewards. This ensures efficient task completion with lower computational costs. The simulation results demonstrate that our method achieves the highest rewards in different scenarios. Our method reduces the task discard ratio by 25% compared to the PPO_KLP-based offload strategy.

In the field of aerial photography, complete coverage path planning (CCPP) is the key to improving the task efficiency of unmanned aerial vehicles (UAVs) with a limited battery capacity. Previous CCPP algorithms consisted of Cellular Decomposition (CD) class, Probabilistic Roadmap (PRM) class, and Bio-inspired Neural Network (BINN) class. However, when faced with the complex environment of multiple forbidden areas, CD and PRM have high computational complexity and a long path length, and BINN has a large number of turns. In this paper, an improved back-and-forth (IBF) algorithm is proposed to achieve good performance in these three aspects at the same time based on a newly straight-turn mode and the corresponding auxiliary approaches (i.e. Local Traversal, Global Traversal, and continuity constraint function). An important difference between straight-turn mode and back-and-forth mode is that the next straight direction is not restricted to being parallel to the last straight direction but is determined by Local Traversal, which is introduced to evaluate the benefits of different paths and find the best direction for the next straight-turn mode at the ending cell. Global Traversal is available to choose a “jump” cell when "Dead zone" are faced. The continuity constraint function is used to maintain the continuity of the unexplored area. Under the comprehensive consideration of path length, computation time, and number of turns, the simulation and experimental results indicate that the proposed IBF algorithm has better performance in multiple forbidden areas.

In the field of target localization, improving direction-of-arrival (DOA) estimation methods for weak targets in the context of strong interference remains a significant challenge. This paper presents a robust DOA estimator for localizing weak signals of interest in an environment with strong interfering sources that improve passive sonar DOA estimation. The presented estimator combines a multiple-measurement-vector orthogonal matching pursuit (MOMP) algorithm and a dimension-reduced matrix filter with deep nulling (DR-MFDN). Strong interfering sources are adaptively suppressed by employing the DR-MFDN, and the beam-space passband robustness is improved. In addition, Gaussian pre-whitening is used to prevent noise colorization. Simulations and experimental results demonstrate that the presented estimator outperforms a conventional estimator based on a dimension-reduced matrix filter with nulling (DR-MFN) and the multiple signal classification algorithm in terms of interference suppression and localization accuracy. Moreover, the presented estimator can effectively handle short snapshots, and it exhibits superior resolution by considering the signal sparsity.

3D point cloud semantic segmentation has been widely used in industrial scenes and has attracted continuous attention as a critical technology for understanding the intelligent robot scene. However, extracting visual semantics in complex environments remains a challenge. We propose the Seg-PointNet model based on multi-layer residual structure and feature pyramid for the LiDAR point cloud data semantic segmentation task in the complex substations scene. The model is based on the PointNet network and introduces a multi-scale residual structure. The residual structure multilayer perception (RES-MLP) model is proposed to fully excavate features at different levels and improve the characterization capabilities of complex features. Moreover, the 3D point cloud feature pyramid module is proposed to characterize the substation scene’s semantic features. We tested and verified the Seg-PointNet model on a self-built substation cloud point (SCP) dataset. The results show that the proposed Seg-PointNet model effectively improves the point cloud data segmentation accuracy, with an accuracy of 89.23% and mean intersection over union (mIoU) of 63.57%. This shows that the model can be applied to substation scenarios and provide technical support to intelligent robots in complex substation environments.