Based on Improved Bio-Inspired Model for Path Planning by Multi-AUV

Abstract

Aiming at path planning and collision avoidance of multiple autonomous underwater vehicle (AUV) system under complex environment, an improved neural network algorithm based on biological inspired model is proposed. Firstly, establishing an improved bio-inspired neural network model, the two-dimensional working area is rasterized, and each grid and neuron are one-toone correspondence, stipulating that the interest area and the obstacle area of the grid correspond to the excitatory and inhibition of neurons respectively, affecting the neurons activity in the whole working area by the transversal function of the adjacent neurons each other. Secondly, AUV plans a safe and collision-free path by comparing the size of the activity of neighbor neurons. Then, Aiming at the problem that AUV moves clinging to the edge of obstacles, adding lateral inhibitory effects of the obstacles on the neural network and greatly improving the safety and rationality of the path planning. Finally, changing the property of grid positions of each AUV in real time to realize collision avoidance between multi-AUV. Simulation experiments prove that the improved algorithm is valid about the path planning in this thesis and the large allowance collision avoidance problem in a complex environment with single-AUV and multi-AUV.

Adaptive Metaheuristic-Based Methods for Autonomous Robot Path Planning: Sustainable Agricultural Applications

“…The methods in the first three categories suffer from high time complexity and local minima trap, especially when mobile robots face multiple constraints when planning a path. Metaheuristic algorithms, a set of nature-inspired algorithms, are the fourth category in this taxonomy that imitate natural, biological, interactive behaviors or physical events [44,45]. These methods try to find an almost optimal path by eliminating the process of creating complex environment models based on stochastic approaches.…”

Research Progress of Path Planning Methods for Autonomous Underwater Vehicle

“…BNN can quickly and efficiently plan a feasible path in the unknown environment with static obstacles of different shapes, including U shape, polygon shape, square shape, and rectangle shape [79]. Wu et al added the lateral inhibition of obstacles to the neural network to solve the problem of AUV moving along the edges of obstacles and improve the safety and rationality of path planning [81]. However, the BNN algorithm does not consider ocean currents and 3D dynamic environments.…”