Coordinating motion of cooperative mobile robots through visual observation

This paper describes the development of an integrated autonomous multi-robot system, where two heterogeneous robots exhibit coordinated convoying behavior. Coordination is accomplished without any communication but by visual observation. An active perception system uses visual servoing to track the leading vehicle to determine its heading and relative distance. A fuzzy logic based real-time motion controller uses the heading to control the steering and relative distance and velocity information to adjust the speed to let the trailing robot smoothly follow the leader. A novel correlation algorithm based on minimum noise and correlation energy (MINACE) filter is used for object tracking. The MINACE based tracker is adaptive and when the tracking degrades due to the change in appearance of the leading robot a new filter is synthesized online to replace the old one. The performance and robustness of the convoying system has been verified in a series of extensive laboratory trials