Unmanned Aerial Vehicle (UAV) Path Planning Based on Improved Pre-planning Artificial Potential Field Method

Abstract

The improvement of Artificial Potential Field Method (APF) is proposed for the problem that the existence of local minimum severity of the traditional artificial force field method leads to the failure of path planning. This method introduces the Rapidly-exploring Random Trees (RRT) algorithm for path pre-planning and generates a pre-planned path from start to finish. This algorithm takes the pre-planned path node as the new gravitational source, weakens the role of target point and emphasizes the path coherence. In the process of path planning, the function of the repulsive potential field is improved to ensure the accessibility of the gravitational source and to guarantee the success of path planning. The simulation results show that the method can effectively avoid local minimum values and has good adaptability.