Reinforcement Learning for Robot Navigation Using Hex-grid Maps

摘要：

　　For some rodent mammals when they foraging or looking for a target, the positions and headings in their brain cells are distributed as a hexagonal raster shape.Hex-grid maps used in the navigation of the enhanced learning robots may have a better performance than the traditional squaregrid maps.In this paper, a new reinforcement learning based robot navigation method is proposed using hex-grid maps.The hex-grid map-building methods and the reinforcement learning based navigation approach in a hex-grid environment are introduced consequently.Several groups of comparative simulation experiments are carried out and the results demonstrate the advantages and efficiency of the proposed method.

关键词： Reinforcement Learning Hex-gird Map Robot Navigation Q-learning

作者: Zhu Yuanyang Xie Donghan Wei Qing Chen Chunlin

作者单位: Department of Control and Systems Engineering, School of Management and Engineering,Nanjing University, Jiangsu, Nanjing, 210093

会议类型: 国内会议

会议名称: 第20届中国系统仿真技术及其应用学术年会(20th CCSSTA 2019)

会议地点: 合肥

会议语种:英文

页码: 527-533

在线出版日期: 2019-08-01（万方平台首次上网日期，不代表论文的发表时间）