Integrating multiple particle filter into a logic framework for robot fault diagnosis

Abstract

Fault detection and diagnosis (FDD) are increasingly important for wheeled mobile robots (WMRs). Particle filter is a promising approach for robot fault diagnosis. In this paper, rule based inference and multiple particle filters are integrated to diagnose hard faults of WMR's internal sensors. The rule based inference method is employed to determine the states of movement of the robot. Each state of movement is monitored with a particle filter. This approach overcomes some shortcomings of general particle filter such as its lack of logic inference capability, decreases particle number and increases efficiency and accuracy for each particle filter. Experiments of monitoring 32 kinds of operation mode of internal sensors of a mobile robot in plane show the accuracy and efficiency of the methods introduced in the paper