FAULT DIAGNOSIS FOR WHEELED MOBILE ROBOTS BASED ON ADAPTIVE PARTICLE FILTER

摘要：

An adaptive particle filter for fault diagnosis of dead-reckoning system was presented. It provided a general framework to integrate rule-based domain knowledge into particle filter. Domain knowledge was exploited to constrain the state space to certain subset. The state space is adjusted by setting the transition matrix. Two typical advantages of this method are: (1) particles will never be drawn from hopeless area of the state space; (2) the particle numbers is reduced.The method is testified in the problem of fault diagnosis for wheeled mobile robots.

关键词： Mobile robot Fault diagnosis Particle filter

作者: ZHUO-HUA DUAN ZI-XING CAI

作者单位: Department of Computer, School of Information Engineering, Shaoguan University, Shaoguan 512003, Chi School of Information Science and Engineering, Central South University, Changsha 410083, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 370-374

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）