Efficient Failure Detection on Mobile Robots Using Particle Filters with Gaussian Process Proposals
Christian Plagemann, Dieter Fox, Wolfram Burgard
The ability to detect failures and to analyze their causes is one of the preconditions of truly autonomous mobile robots. Especially online failure detection is a complex task, since the effects of failures are typically difficult to model and often resemble the noisy system behavior in a fault-free operational mode. The extremely low a priori likelihood of failures poses additional challenges for detection algorithms. In this paper, we present an approach that applies Gaussian process classification and regression techniques for learning highly effective proposal distributions of a particle filter that is applied to track the state of the system. As a result, the efficiency and robustness of the state estimation process is substantially improved. In practical experiments carried out with a real robot we demonstrate that our system is capable of detecting collisions with unseen obstacles while at the same time estimating the changing point of contact with the obstacle.