Vision Based Real-time Localization of Multiple Mobile Robots

This paper describes the design of a vision based real-time localization system capable of tracking multiple robots in a real-time fashion. A fuzzy framework is used to describe the system in a way that is implementation independent while being easily deployed using standard hardware and software. The proposed architecture allows the use of multiple cameras and can be easily implemented in a parallel system. One of the advantages of this system is that it provides not only an estimate of a robot position but also a certainty measure of that estimate. That can be very useful, for example, if we want to feed the estimate to a Kalman filter.