Fault Detection and Identification for Mobile Robots

Sponsor

  • JPL/NASA

Summary

Autonomous vehicles comprise numerous electromechanical and sensory components that are susceptible to failures. Real-time detection of potential fault modes is a necessary condition for the reliable execution of any task. We have designed and implemented arrays of model-based diagnostic estimators that monitor the health status of a wheeled robot, detect and identify temporary or permanent failures, and provide appropriate information for selecting amongst various reconfigurable control strategies.

Block Diagram

Block diagram of two parallel Kalman filters.

Relevant Publications

  • C3. P. Goel, G. Dedeoglu, S.I. Roumeliotis, and G.S. Sukhatme, "Fault Detection and Identification in a Mobile Robot Using Multiple Model Estimation and Neural Network" . In Proc. 2000 IEEE International Conference on Robotics and Automation, San Francisco, California, April 22-28, pp. 2302-2309. (pdf )

  • C2. S.I. Roumeliotis, G.S. Sukhatme, and G.A. Bekey, "Sensor Fault Detection and Identification in a Mobile Robot". In Proc. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems, Victoria, Canada, Oct. 13-17, 1998, pp.1383-1388. (pdf )

  • C1. S.I. Roumeliotis, G.S. Sukhatme, and G.A. Bekey, "Fault Detection and Identification in a Mobile Robot using Multiple-Model Estimation". In Proc. 1998 IEEE International Conference on Robotics and Automation, Leuven, Belgium, May 16-21, 1998, pp. 2223-2228. (pdf )