By studying the local collision avoidance path planning of underwater unmanned vehicle,and improving the artifical potential field method and the speed obstacle method,a method to redistribute the repulsive force in three-dimensional space is proposed,which combines the artifical potential field method and the speed obstacle method. The artifical simulation potential field is established to obtain the resultant force,and the underwater unmanned vehicle is guided through the direction of the resultant force to complete the avoidance of dynamic and static obstacles. The simulation results show that this method can effectively complete collision avoidance in a mixed dynamic and static environment,and the smoothed path is more suitable to the actual navigation and collision avoidance requirements of unmanned underwater vehicles.
[4] ZENG X M,ITO M.Planning a collision avoidance model for ship using genetic algorithm[C]//2001 IEEE International Conference on Systems,Man and Cybernetics.IEEE,2002
[5] TSOU M C,SUEH C K.The study of ship collision avoidance route planning by ant colony algorithm[J].Journal of Marine Science and Technology,2010,18(5).
[6] WOO J,KIM N.Collision avoidance for an unmanned surface vehicle using deep reinforcement learning[J].Ocean Engineering,2020,199c.