Development of an integrated path planning algorithm for autonomous driving of unmanned surface vessel

Abstract

This paper proposes a path planning and obstacle avoidance algorithm for USV(Unmanned Surface Vessel). Path planning for autonomous driving is largely classified into global path generation and regional path generation. First, the A* algorithm is used when creating the global path. At this time, when applying the simple A* algorithm, since the rotation radius and dynamic characteristics of USV are not taken into account, a path generated from the A* algorithm is modified by applying a cardinal spline. Next, the P-DWA (Predictive-Dynamic Window Approach) algorithm was applied to avoid the fixed/moving obstacles of the local path and follow the waypoints generated from the global path.