An Improved Artificial Potential Field Path Planning Based on Gradient Statistical Mutation Quantum Genetic Algorithm

In the field of vehicle path planning, the traditional Artificial Potential Field (APF) has the disadvantage that it is difficult to jump out of the local extremum. Therefore, an improved Artificial Potential Field based on the Gradient Statistical Mutation Quantum Genetic Algorithm (GSM-QGA) is proposed. Based on the traditional circular influence domain, the dynamic elliptical influence domain of the repulsive potential field is proposed by analyzing the motion state of the vehicle and obstacles. Through an analysis of the factors influencing the potential field function, the velocity factor is introduced to design the repulsive and attractive potential field functions. The GSM-QGA is introduced as a modified local optimal correction strategy for the improved APF. When the vehicle falls into the local extremum reciprocating motion, a pseudo-global map is constructed based on the current position of the vehicle, and a feasible path to jump out of the local extremum range is planned. The effectiveness of the improved algorithm in vehicle path planning is proved by simulation experiments. Compared with other algorithms, the path length planned by the improved algorithm is shorter and the path is smoother. The algorithm can effectively jump out of the local optimal state.