A practical path planning and navigation algorithm for an unmanned surface vehicle using the fast marching algorithm

Abstract

There has been an increasing interest in the development of unmanned surface vehicles (USVs) in recent decades. As USVs are required to carry out complex missions without any human intervention in various environments, an intelligent path planning algorithm is critical. A path planning algorithm is able to utilise environment data to calculate an optimal trajectory to guarantee safety. To achieve this, in this paper, a novel path planning and navigation (PN) algorithm is proposed. The PN algorithm uses the fast marching method (FMM) as the base algorithm to search for an optimal collision-free trajectory. Then, to facilitate the trajectory tracking of the USV, a new waypoint-generator based on the line-of-sight (LOS) is developed to generate the optimal number of waypoints from the path. The proposed algorithm has been evaluated based on the Springer USV, and has been shown that it can be seamlessly integrated with the Springer's exiting autopilot to achieve full autonomy.