A Path-Planning Method Considering Environmental Disturbance Based on VPF-RRT*

In the traditional rapidly exploring random tree (RRT) algorithm, planned path is not smooth, distance long, and fault tolerance rate of low. Disturbances in an environment can cause unmanned surface vessels (USVs) to deviate from their during navigation. Therefore, this paper proposed a path-planning method considering environmental disturbance based on virtual potential field RRT* (VPF-RRT*). First, basis VPF-RRT* algorithm for planning path. Second, anti-environmental deep recurrent neural networks PI (DRNN-PI) controller allow USV eliminate maintain its track along Comparative simulation experiments between other algorithms were conducted within two different experimental scenes. experiment, had shorter smaller total turning angle when compared algorithm. path-tracking using could effectively compensate impact navigation order avoid contingency experiment verify effectiveness generality three conducted. The results