Obstacle Prediction-based Dynamic Path Planning for a Mobile Robot

Abstract

A path-planning method based on a combination of the static global and the dynamic local pathplanning methods is proposed for robot path planning under a complex environment. There are known static obstacles and unknown dynamic obstacles in any complex environment. The local-path planner dynamically generates a local path using obstacle-motion prediction and a rolling window for dynamic path planning to partially adjust the global path. Simulation results show that the mobile robot achieves both overall and local obstacle-avoidance during motion, in association with an optimum path, which verifies the feasibility and effectiveness of the method.