Research on obstacle avoidance path planning based on improved artificial potential field method

Abstract

To overcome the limitations of the traditional artificial potential field method, including local minima, unreachable targets, path oscillations, and insufficient consideration of road structure information, this paper proposes an improved potential field algorithm for path planning on structured roads. Based on the conventional attractive and obstacle repulsive forces, a novel road boundary repulsive potential field is introduced to constrain the lateral driving range of the vehicle. A forward auxiliary force is introduced to break the force balance and escape from local minima. A combined force-limiting and dynamic position update mechanism is designed to suppress trajectory mutations. A scenario with a length of 100 m and a width of 4 m containing 5 dynamic obstacles is constructed for verification. The results show that the improved algorithm enables the vehicle to reach the target point without stopping or reversing in a continuous obstacle scenario, with a target reach-ability rate of over 99% and a terminal error of less than 0.3 meters. The maximum lateral deviation of the planned trajectory is less than 0.5 m, the average curvature is less than 0.08 m⁻¹, and no boundary crossing or collision occurs throughout the entire process. The generated trajectory is smooth and fully compatible with the vehicle's kinematic characteristics.