Building Hybrid Rover Models for NASA: Lessons Learned
Particle filters have recently become popular for diagnosis and monitoring of hybrid systems. In this paper we describe our experiences using particle filters on a real diagnosis problem, the NASA Ames Research Center's K-9 rover. As well as the challenge of modelling the dynamics of the system, there are two major issues in applying a particle filter to such a model. The first is the asynchronous nature of the system-observations from different subsystems arrive at different rates, and occasionally out of order, leading to large amounts of uncertainty in the state of the system. The second issue is data interpretation. The particle filter produces a probability distribution over the state of the system, from which summary statistics that can be used for control or higher-level diagnosis must be extracted. We describe our approaches to both these problems, as well as other modelling issues that arose in this domain.