Research on Mobile Robot path Planning Based on improved QLearning
Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China
Proceedings: ICMLCA 2021
Pages: 5Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Cui, Xujing; Liu, Zihong; Shi, Zhengjin; Xie, Feng; Wang, Bolun (School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, China)
Fan, Xiaoliang (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China & Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China)
Abstract:
With the wide application of indoor mobile platforms, path planning is a significant challenge for the autonomous navigation of mobile robots. Generally, in an indoor environment, the ground mobile platform cannot obtain the interaction and perception of the destination and the surrounding. And cannot effectively plan a collision-free path, accurately. To address this problem, we propose to adopt a new search strategy and enhanced orientation based on the traditional Q-learning algorithm, which reduces the possibility of falling into local optimal and speeds up the learning efficiency. The simulation results show that our method can quickly and accurately realize the path planning and fully autonomous navigation of the indoor ground mobile platform. In structured spaces represented by storage centers, unmanned chemical factories and prisons, our method is more suitable for practical application scenarios of the indoor ground mobile platform.