Path Planning Method Based on Extended Random Artificial Potential Field

Abstract

The artificial potential field method is a commonly used algorithm for robot local path planning. However, it is prone to the issues of falling into local minima and generating paths that do not adhere to the robot’s kinematics. In light of this, we have proposed an enhanced approach called the stochastic artificial potential field method. By filtering the obstacle locations and introducing a randomly directed repulsive force within a specific angular range, we address the problem of unbalanced forces on the robot, thereby mitigating the issue of falling into local minima. Furthermore, we eliminate oscillations and sharp bends in the robot’s trajectory through Bessel optimization. Experimental results demonstrate that the stochastic artificial potential field method effectively resolves the challenges of local minima and path conformity with robot kinematics.