Research on robot path planning by integrating state-based decision-making A* algorithm and inertial dynamic window approach

Abstract

In response to challenges faced by mobile robots in global path planning within high-resolution grid maps—such as excessive waypoints, low efficiency, inability to evade random obstacles, and poor maneuverability in narrow passage environments during local path planning—a robot path planning algorithm is proposed. This algorithm integrates state-based decision-making A* algorithm with inertial dynamic window approach. Firstly, the exploration method of the A* algorithm is enhanced to dynamically adapt to the current state of the mobile robot, reducing the number of exploration nodes to improve exploration efficiency. Redundant turning points are eliminated from the original planned path to optimize the global path. Next, a path deviation evaluation function is incorporated into the speed space evaluation function of the dynamic window approach. This function adds weight to forward movement along the original direction, enhancing the robot’s ability to navigate through narrow environments. Finally, key points of the global path are used as sub-goals for local path planning, achieving a fusion of approaches. This enables the robot to simultaneously determine the optimal global path and perform random obstacle avoidance. Experimental verification demonstrates that deploying this integrated algorithm enhances exploration efficiency, reduces path turning points, achieves random obstacle avoidance, and excels in narrow passage environments for mobile robots.