Obstacle Recognition for a Service Mobile Robot Based on RFID with Multi-Antenna and Stereo Vision

In this paper,a novel method of obstacle recogni- tion and localization for mobile robots using radio frequency identi .cation (RFID)technology and stereo vision is proposed as it is inexpensive,.exible and easy to use in practical envi- ronments.As information about the obstacles or environment can be written in ID tags,the proposed method can detect the obstacles easily and quickly compared with other methods.By considering the probabilistic uncertainty of RFID,we introduce Bayes rule to calculate probability where the ID tag exists. But the accuracy of localization of obstacles is not enough for mobile robot navigation just using one antenna.In this paper, we discuss using multi-antennas to localize obstacle with ID tags. After localizing ID tag,the stereo camera starts to process the image of the region of interest where the obstacle exists.The proposed method does not need to process all the image and easily gets some information about obstacles such as size,and color,and thus decreases the processing computation.This paper introduces the architecture of the proposed method and some experimental results.
RFID stereo camera recognition mobile robot localization.
Songmin Jia Jinbuo Sheng Kunikatsu Takase
Graduate School of Information Systems University of Electro-Communications 1-5-1 Chofugaoka,Chofu-City,Tokyo 182-8585,Japan
国际会议
2008 IEEE International Conference on Onformation and Automation(IEEE 信息与自动化国际会议)
张家界
英文
125-130
2008-06-20(万方平台首次上网日期,不代表论文的发表时间)