Rastreamento de objeto esférico por cooperação multi-robô

Abstract

In Mobile Robotics, where visual tracking is an extremely important subproblem, one of the solutions found to reduce the problems arising from partial and total occlusion is the use of multiple robots. A system was implemented to investigate the impacts of data fusion on multi-robot visual tracking in three-dimensional space on the occurrence of partial and total occlusion. The system has two approaches to visual tracking of a spherical object. The rst is non-cooperative visual tracking where only the data from a single robot is used. The second is a cooperative visual tracking where the data from a team of robots is fused using a particle lter. To evaluate both approaches, a visual tracking environment with partial and total occlusions was simulated where the tracking was performed by a team of robots. The result of the experiment shows that the noncooperative approach presented a lower computational cost than the cooperative approach but the inferred trajectory was impaired by the occlusions, a fact that did not occur in the cooperative approach due to the data fusion.