基于多超声传感器信息和NeuCube的移动机器人走廊-计算机应用.PDF

基于多超声传感器信息和 NeuCube 的移动机器人走廊场景识别 1* 2 1 2 3 4 王秀青 , 侯增广 , 潘世英 , 谭民 , 王永吉 , 曾慧 1(河北师范大学 应用信息技术系, 石家庄 050024) 2( 中国科学院 自动化研究所 复杂系统管理与控制国家重点实验室，北京 100190) 3( 中国科学院 软件研究所 基础软件国家工程研究中心，计算机科学国家重点实验室, 互联网软件技术实验室，北 京 100190) 4 (北京科技大学 信息学院, 北京 100083) Corridor Scene Recognition for Mobile Robots Based on Multi-sonar-sensor information and NeuCube 1* 2 1 2 3 4 WANG Xiu-Qing , HOU Zeng-Guang , PAN Shi-Ying , TAN Min , WANG Yong-Ji , ZENG Hui 1(Department of Information and Technology, Hebei Normal University, Shijiazhuang 050024, China) 2(Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing 100090, China) 3(National Engineering Research Center for Fundamental Software, Laboratory for Interact Software Technologies, State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China) 4(School of Information, University of Science and Technology Beijing, Beijing 100083, China) Abstract : To improve the perception ability of indoors mobile robots, the classification method for the commonly structured corridor-scenes, Spiking neural networks (SNNs ) and NeuCube, which is a novel computing model based on SNNs, are studied. SNNs can convey spatio-temporal information by spikes. Besides, SNNs is more suitable for analyzing dynamic and time-series data, and for recognizing data of various patterns than traditional neural networks (NNs). The principle, learning methods and calculation steps of NeuCube were discussed. The seven common corridor scenes were recognized by the classification method based on multi-sonar-sensor information and NeuCube. Th