During the process of reverse parking, it is difficult to achieve the ideal reference trajectory while avoiding collision. In this study, with the aim of establishing reference trajectory optimization for automatic reverse parking that smooths and shortens the trajectory length and ensures the berthing inclination angle is small enough, an improved immune moth–flame optimization method based on gene correction is proposed. Specifically, based on the standard automatic parking plane system, a reasonable high-quality reference trajectory optimization model for automatic parking is constructed by combining the cubic spline-fitting method and a boundary-crossing solution based on gene correction integrated into moth–flame optimization. To enhance the model’s global optimization performance, nonlinear decline strategies, including crossover and variation probability and weight coefficient, and a high-quality solution-set maintenance mechanism based on fusion distance are also designed. Taking garage No.160 of the Dalian Shell Museum located in Dalian, Xinghai Square, as the experimental site, experiments on automatic parking reference trajectory optimization and tracking control were carried out. The results show that the proposed optimization algorithm provides higher accuracy for reference trajectory optimization and can achieve better tracking control of the reference trajectory.

Deep Q Network (DQN) plays a crucial role in path planning for autonomous mobile robots. The traditional DQN algorithm has problems such as slow convergence speed and being prone to falling into local optima in path planning tasks. To address these issues, this paper proposes an improved DQN algorithm for path planning of autonomous mobile robots. Firstly, the reward function is improved based on heading angle error and distance, and the DHD (distance- heading angle- direction) reward function is designed by combining the motion direction to improve the performance of the algorithm and avoid local optima. Secondly, a weight-sampling learning strategy is designed to increase the utilization rate of training samples and expedite the algorithm's convergence speed. Finally, through comparative simulation experiments, it is verified that the improved DQN algorithm has better performance than traditional DQN and prioritized experience replay.