Xinyu Hu

Multiple autonomous underwater vehicles (MAUVs) cooperative systems are extensively extensively utilized for conducting search missions of wrecked aircraft or submarines across vast oceanic areas. Ensuring safe and efficient complete coverage path planning is a critical challenge for MAUVs in performing these search tasks. In this paper, we present an efficient MAUVs cooperative adaptive coverage path planning algorithm. Specifically, we introduce the neuronal activity reassigned (NAR) algorithm as the initial step to devise optimal navigation paths for a single AUV. Through the utilization of both the AUV steering number optimization strategy and the deadlock point escape algorithm based on the glasius bio-inspired neural network (GBNN), the path planning process is jointly optimized. Then, the adaptive balance evolution (ABE) algorithm is designed with the AUV energy constraints as a guide to match each AUV to a subtask sea area with task volume differentiation by dividing the task sea area in multiple iterations based on the residual capacity difference of individual AUVs. Finally, the simulation and experiment results demonstrate that the MAUVs cooperative adaptive coverage path planning algorithm proposed in this paper offers several advantages, including optimal task balance, extensive coverage, minimal path repetition rate, reduced occurrence of deadlock points, and decreased steering times. These benefits are instrumental in facilitating the MAUVs system’s efficient execution of refined search tasks.

In scenarios such as volcanic eruption forecasting, seabed exploration, and subsea pipeline inspection, multi-autonomous underwater vehicle (AUVs) system is required to autonomously achieve close-range detection of target areas under mission constraints. This process relies on information exchange-based collaborative task planning, but disturbances from complex underwater environments and ocean currents directly affect the efficiency and safety of Multi-AUVs cooperation. A semi-closed ring bionic self-organizing map (SRBSOM) algorithm is proposed in this paper, which takes the mission urgency, currents and traveling salesman problem into consideration, and combines the hybrid bionic iterative network model, dynamic competitive assignment mechanism and semi-closed ring optimization to achieve dynamic task assignment for AUVs. Additionally, path post-processing and reorganization is performed through window filtering and corner smoothing, reducing control complexity and collision risks at turning points. Simulation results validate the environmental adaptability of the SRBSOM algorithm, which can provide a novel solution for the traffic planning of unmanned platforms in underwater environments.

Addressing challenges like ocean currents, dynamic obstacles, collision avoidance, and computing limitations, a hybrid algorithm is proposed for multi-AUVs to search for random static or dynamic targets in a 3D marine environment and the environment is characterized by our Task Urgency Biological Neural Network (TUBNN) model, encapsulates factors such as currents, obstacles, and targets using neuronal activity representations. For optimizing task assignments in the face of unpredictable oceanic variables, a Double Layer Biological Self-organizing Map (DLBSOM) algorithm is proposed. Post assignment, the initial path, generated via DLBSOM, is refined by the end-to-end direct connection model to eliminate superfluous routes. Enhanced by the A $^\ast$ algorithm and Fermat’s spiral curve, our approach ensures paths align with AUV navigational constraints. Integrating real-time sonar data, our Distance-Speed Comprehensive Evaluation (DSCE) strategy, combined with the local dynamic neural network, facilitates the avoidance of unforeseen barriers, ensuring safe AUV navigation. The correction redistribution mechanism, leveraging live data and assessing AUV and target statuses, refines task assignment. We holistically evaluate environmental, cooperative, and AUV-specific constraints, with our algorithm’s efficacy validated through rigorous theoretical analysis, simulations, and field tests.

When performing cooperative search operations underwater, multi-autonomous underwater vehicles formations may encounter array-type obstacles such as gullies and bumps. To safely traverse the obstacle domain, this paper balances convergence time, transformation distance and sensor network power consumption, and proposes a Formation Comprehensive Cost (FCC) model to achieve collision avoidance of the formations. The FCC model is used instead of the fitness function of the genetic algorithm to solve the assignment of capture positions and the improved neural self-organizing map (INSOM) algorithm is proposed to achieve efficient path-planning during the capture process. The simulation experiments in 3D space verify that the proposed scheme can improve the efficiency of robot deployment while ensuring safety.

The problem of aircraft entering and exiting water is a complex, nonlinear, strongly disturbed, and multi-coupled multiphase flow problem, which involves the precise capture of the air/water interface and the multi-coupling interaction between aircraft, water, and air. Moreover, due to the large difference in medium properties during the crossing, the load on the body will suddenly change. In this paper, the VOF (volume of fluid) algorithm is used to capture the liquid surface at the air/water interface, and since body movement is involved in this process, the overset grid technology is used to avoid the traditional dynamic grid deformation problem. In the process of this numerical simulation prediction, the effects of different water-entry angles and different water-entry heights on the body load and attitude of the trans-medium aircraft, as well as the cavitation evolution law of the body water entry are analyzed. On this basis, to simulate the authenticity and complexity of the water-entry environment, numerical wave-making technology was introduced to analyze the water-entry load, posture, and cavitation evolution law of the body under different wave environments. The numerical parameters under the condition of wave and no wave are compared, and the difference in water-entry performance under the condition of wave and no wave is analyzed.

A trans-medium aircraft is a new concept aircraft that can both dive in the water and fly in the air. In this paper, a new type of water–air multi-medium span vehicle is designed based on the water entry and exit structure model of a multi-rotor UAV. Based on the designed structural model of the cross-media aircraft, the OpenFOAM open source numerical platform is used to analyze the single-medium aerodynamic characteristics and the multi-medium spanning flow analysis. The rotating flow characteristics of single-medium air rotor and underwater propeller are calculated by sliding mesh. In order to prevent the numerical divergence caused by the deformation of the grid movement, the overset grid method and the multiphase flow technology are used for the numerical simulation of the water entry and exit of the cross-medium aircraft. Through the above analysis, the flow field characteristics of the trans-medium vehicle in different media are verified, and the changes in the body load and attitude at different water entry angles are also obtained during the process of medium crossing.

In this paper, we propose a modified hybrid Salp Swarm Algorithm (SSA) and Aquila Optimizer (AO) named IHSSAO for UAV path planning in complex terrain. The primary logic of the proposed IHSSAO is to enhance the performance of AO by introducing the leader mechanism of SSA, tent chaotic map, and pinhole imaging opposition-based learning strategy. Firstly, the tent chaotic map is utilized to substitute the randomly generated initial population in the original algorithm to increase the diversity of the initial individuals. Secondly, we integrate the leader mechanism of SSA into the position update formulation of the basic AO, which enables the search individuals to fully utilize the optimal solution information and enhances the global search capability of AO. Thirdly, we introduce the pinhole imaging opposition-based learning in the proposed IHSSAO to enhance the capability to escape from the local optimization. To verify the effectiveness of the proposed IHSSAO algorithm, we tested it against SSA, AO, and five other advanced meta-heuristic algorithms on 23 classical benchmark functions and 17 IEEE CEC2017 test functions. The experimental results indicate that the proposed IHSSAO is superior to the other seven algorithms in most cases. Eventually, we applied the IHSSAO, SSA, and AO to solve the UAV path planning problem. The experimental results verify that the IHSSAO is superior to the basic SSA and AO for solving the UAV path planning problem in complex terrain.