Multi-Tree Guided Efficient Robot Motion Planning

Motion Planning is necessary for robots to complete different tasks. Rapidly-exploring Random Tree (RRT) and its variants have been widely used in robot motion planning due their fast search the state space. However, they perform not well many complex environments since needs simultaneously consider geometry constraints differential constraints. In this article, we propose a novel algorithm that utilizes multi-tree guide exploration exploitation. The proposed maintains more than two trees space at first. Each tree will explore local environments. starts from root gradually collect information other grow towards goal state. This simultaneous exploitation method can quickly find feasible trajectory. We compare with popular algorithms. experiment results demonstrate our performs better on evaluation metrics.