Research and Implementation of USV by Adaptive Collision Avoidance Algorithm in Mixed Scenarios

Abstract During the mission of USV (Unmanned Surface Vehicle), there may be some static or dynamic obstacles on pre-planned track that are not displayed ground station. To avoid these in time, a model DCPA (distance to closest point approach) between and obstacle is proposed, which used plan speed USV, adaptively accelerate decelerate can safely obstacles. We solved problem target unreachable heading change optimization by planning at IAPF (improved artificial potential field) process sailing, effectively respond collision avoidance emergencies. The outputs set behavior vectors (speed, heading), hands it over controller control navigation USV. In this study, an adaptive method improve ability mixed scene Through multiple launching experiments, actual effect verified, safety reliability application requirements met.