Projects

Context-Aware Multi-Robot Coordination

In this work, we consider several autonomous robots that need to coordinate to accomplish a common goal. Specifically, we assume that they are provided with a contextual knowledge about the scenario they operate in. To this end, we contribute an approach to coordinate a team of robots able to exploit this contextual knowledge to enhance the overall performance. This is achieved, by adapting the underlying task assignment and distributed world representation, depending on the context of operation. We apply our context-aware coordination to the problem of locating a moving, non-adversarial target. In this specific application, multiple sub-areas of the environment are first ranked based on the provided contextual knowledge. The robots then coordinate adaptively to efficiently locate the moving target. The complete context-aware search approach runs on several robots. We report on experiments carried out with a team of humanoid robots in a soccer scenario and a team of mobile bases in an office environment.