A simple implement of Q-learning in robot path planning

Abstract

This paper firstly gives an introduction of robot path planning problem, which includes the brief definition of path planning, some representative methods and previous applications of Q-learning. Secondly, the paper compares some typical methods, like Breadth First Search and Depth-First-Search, A* and deep learning, with corresponding pseudo codes in detail. Their advantages and disadvantages are also listed in this part. Thirdly, we carry out a simple simulation experiment by applying Q-learning method. The experiment is clearly presented in several parts which includes environment establishment, realizing the Q-learning, simulation experiment and interpretation of the Q-table. In the end, a short conclusion summarizes the achievement of our results.

2D LiDAR Based Reinforcement Learning for Multi-Target Path Planning in Unknown Environment

“…Lieping Zhang [23] proposed a Self-Adaptive Reinforcement-Exploration Q-learning (SARE-Q) method in various grid state space environments and compared the results to those of previous CQL and Self-Adaptive Q-learning (SA-Q). Conghao Jin et al [24] and Haoran Gao et al [25] both successfully implemented CQL for path planning in grid state space simulation environments, and both agents were able to learn how to find the desired path. However, their results were not compared to any other path planning methods.…”