An adaptive particle filter for mobile robot fault diagnosis

Abstract

An adaptive particle filter for fault diagnosis of dead-reckoning system was presented, which applied 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 was adjusted by setting the transition matrix. Firstly, the monitored mobile robot and its kinematics models, measurement models and fault models were given. Then, 5 kinds of planar movement states of the robot were estimated with driving speeds of left and right side. After that, the possible (or detectable) fault modes were obtained to modify the transitional probability. There are two typical advantages of this method, i.e. particles will never be drawn from hopeless area of the state space, and the particle number is reduced.

Keywords

mobile robot / fault diagnosis / particle filter / adaptive

References

[1] CaiZ.-x., HeH.-g., ChenH.. Some issues for mobile robot navigation under unknown environments[J]. Control and Decision, 2002, 17(4): 385-390

[2] Roumeliotis S I, Sukhatme G S, Bekey G A. Sensor fault detection and identification in a mobile robot[C]// IEEE/RSJ Int Conf on Intelligent Robots and Systems. Victoria, Canada, 1998: 1383–1388.

[3] Goel P, Dedeoglu G, Roumeliotis S I, et al. Fault detection and identification in a mobile robot using multiple model estimation and neural network[C]// IEEE Int Conf on Robotics & Automation. San Fancisco, USA, 2000: 2302–2309.

[4] Hashimoto M, Kawashima H, Nakagami T, et al, Sensor fault detection and identification in dead-reckoning system of mobile robot: interacting multiple model approach[C]// Int Conf on Intelligent Robots and Systems, 2001: 1321–1326.

[5] VermaV., GordonG., SimmonsR., et al.. Real-time fault diagnosis [robot fault diagnosis[J]. IEEE Robotics & Automation Magazine, 2004, 11(2): 56-66

[6] VermaV., LangfordJ., SimmonsR.. Non-Parametric fault identification for space rovers[C]. International Symposium on Artificial Intelligence and Robotics in Space(iSAIRAS), 2001, Montreal, IEEE Press

[7] VermaV., GordonG., SimmonsR.. Efficient monitoring for planetary rovers[C]. International Symposium on Artificial Intelligence and Robotics in Space, 2003, Nara, IEEE Press

[8] ArulampalamM. S., MaskellS., GordonN., et al.. A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking[J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188

[9] KwokC., FoxD., MeilaM.. KLD-Sampling: adaptive particle filters [J]. International Journal of Robotics Research, 2003, 22(12): 985-1003

[10] de Freital N. Rao-Blackwellised particle filtering for fault diagnosis[C]// Proceedings of IEEE Aerospace Conference, Montana, USA, 2002

[11] MoY.-w., XiaoD.-yun.. Hybrid system monitoring and diagnosing based on particle filter algorithm[J]. Acta Automatica Sinica, 2003, 29(5): 641-648

[12] MoY.-w., XiaoD.-yun.. Evolutionary particle filter and its application[J]. Control Theory and Application, 2005, 22(2): 269-272

[13] Verma V, Thrun S, Simmons R. Variable resolution particle filter[C]//. Proceedings of the International Joint Conference on Artificial intelligence. Acapulco, Mexico, 2003

[14] CAI Zi-xing, DUAN Zhuo-hua, CAI Jing-feng, et al. A multiple particle filters method for fault diagnosis of mobile robot dead-reckoning system[C]// 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems. Albert, Canada, 2005: 480–485.

[15] CAI Zi-xing, ZOU Xiao-bing, WANG Lu, et al. A research on mobile robot navigation control in unknown environment: objectives, design and experiences[C]// Proceedings of Korea-Sino Symposium on Intelligent Systems. Busan: 2004: 57–63.