Data-Driven Robot Fault Detection and Diagnosis Using Generative Models: A Modified SFDD Algorithm

TL;DR

This paper introduces a modified SFDD algorithm utilizing generative models, specifically restricted Boltzmann machines, for online robot fault detection, demonstrating promising results on a mobile logistics robot.

Contribution

The paper proposes a novel fault detection framework combining generative models with SFDD for improved robot monitoring capabilities.

Findings

Achieved 88.6% precision and 75.6% recall in fault recognition.

Framework feasibility demonstrated on a mobile logistics robot.

Monitoring performance depends on model choice and parameters.

Abstract

This paper presents a modification of the data-driven sensor-based fault detection and diagnosis (SFDD) algorithm for online robot monitoring. Our version of the algorithm uses a collection of generative models, in particular restricted Boltzmann machines, each of which represents the distribution of sliding window correlations between a pair of correlated measurements. We use such models in a residual generation scheme, where high residuals generate conflict sets that are then used in a subsequent diagnosis step. As a proof of concept, the framework is evaluated on a mobile logistics robot for the problem of recognising disconnected wheels, such that the evaluation demonstrates the feasibility of the framework (on the faulty data set, the models obtained 88.6% precision and 75.6% recall rates), but also shows that the monitoring results are influenced by the choice of distribution model and the model parameters as a whole.