Self-organization of Place Cells and Reward-Based Navigation for a Mobile Robot

摘要：

We investigate a method to navigate a mobile robot by using self-organizing map and reinforcement learning. Modeling hippocampal place cells, the map consists of units activated at specified locations in an environment. In order to adapt the map to a realworld environment, preferred locations of these units are self-organized by Kohonens algorithm using the robots actual position data. Then an actor-critic network is provided the position information from the selforganized map and trained to acquire goaldirected behavior of the robot. It is shown by simulation that the network successfully achieves the navigation avoiding obstacles.

作者: Takashi TAKAHASHI Toshio TANAKA Kenji NISHIDA Takio KURITA

作者单位: Postdoctoral Research Fellow of the Japan Society for the Promotion of Science,The National Institut Neuroscience Research Institute, Tsukuba Central 2,The National Institute of Advanced Industrial Sci

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1202-1207

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）