Graph neural network based method for robot path planning

Abstract

Sampling-based path planning is widely used in robotics, particularly in high-dimensional state spaces. In the path planning process, collision detection is the most time-consuming operation. Therefore, we propose a learning-based path planning method that reduces the number of collision checks. We develop an efficient neural network model based on graph neural networks. The model outputs weights for each neighbor based on the obstacle, searched path, and random geometric graph, which are used to guide the planner in avoiding obstacles. We evaluate the efficiency of the proposed path planning method through simulated random worlds and real-world experiments. The results demonstrate that the proposed method significantly reduces the number of collision checks and improves the path planning speed in high-dimensional environments.