Mobile Robot Path Planning with Integrated Artificial Potential Fields and Q_learning Algorithm
A path planning algorithm that integrates artificial potential field methods with the traditional Q_learning algorithm was proposed to address the issues of slow convergence and the propensity to fall into local optima.The potential field values were introduced to optimize the reward values during state selection,and a virtual potential field was constructed within a grid map.The gravitational function of the artificial potential field was incorporated when initializing the Q-value function,while the repulsive function was intro-duced during the updating of the Q-value function.Finally,the performance of the traditional algorithm and the improved algorithm was compared by simulation experiments.The experimental results show that the convergence time of the improved algorithm is reduced by 21.5％,the planned paths are smoother,and the effectiveness of the proposed method is verified.
path planningartificial potential field methodQ_learningreward values
万方数据
维普
