Fault detection in autonomous robots based on fault injection and learning

Abstract

In this paper, we study a new approach to fault detection for autonomous robots. Our hypothesis is that hardware faults change the flow of sensory data and the actions performed by the control program. By detecting these changes, the presence of faults can be inferred. In order to test our hypothesis, we collect data from three different tasks performed by real robots. During a number of training runs, we record sensory data from the robots while they are operating normally and after a fault has been injected. We use back-propagation neural networks to synthesize fault detection components based on the data collected in the training runs. We evaluate the performance of the trained fault detectors in terms of number of false positives and time it takes to detect a fault. The results show that good fault detectors can be obtained. We extend the set of possible faults and go on to show that a single fault detector can be trained to detect several faults in both a robot's sensors and actuators. We show that fault detectors can be synthesized that are robust to variations in the task, and we show how a fault detector can be trained to allow one robot to detect faults that occur in another robot.

From Fireflies to Fault-Tolerant Swarms of Robots

“…Many studies have been devoted to endogenous fault detection, that is, a robot detecting faults in itself, see for instance [6,7,8,9,10,11,12,13,14]. Some faults are, however, hard to detect in the robot in which they occur.…”

Towards group transport by swarms of robots

“…Therefore, strategies of fault detection and self-repair need to be investigated (Parker, 1999;Tomita et al, 1999;Bererton and Khosla, 2001;Christensen et al, 2008aChristensen et al, , 2008b.…”

In Situ Self-Reconfiguration of Hexapod Robot OSCAR Using Biologically Inspired Approaches

“…For fault detection in general and for the domain of autonomous robots various approaches have been considered like: Time-Delay Neural Networks (TDNN) (Christensen et al, 2008), Recurrent Neural Networks (RNN) (Przystalka, 2006), particle filters (Verma & Simmons, 2006;Zhuo-hua et al, 2006). The mentioned approaches are mostly related to the procedure of synthesizing fault detection components based on the collected data in the training runs.…”