Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

Abstract

The existing dynamic path planning algorithm cannot properly solve the problem of the path planning of wheeled robot on the slope ground with dynamic moving obstacles. To solve the problem of slow convergence rate in the training phase of DDQN, the dynamic path planning algorithm based on Tree-Double Deep Q Network (TDDQN) is proposed. The algorithm discards detected incomplete and over-detected paths by optimizing the tree structure, and combines the DDQN method with the tree structure method. Firstly, DDQN algorithm is used to select the best action in the current state after performing fewer actions, so as to obtain the candidate path that meets the conditions. And then, according to the obtained state, the above process is repeatedly executed to form multiple paths of the tree structure. Finally, the non-maximum suppression method is used to select the best path from the plurality of eligible candidate paths. ROS simulation and experiment verify that the wheeled robot can reach the target effectively on the slope ground with moving obstacles. The results show that compared with DDQN algorithm, TDDQN has the advantages of fast convergence and low loss function.