Adapting Robot Team Behavior from Interaction with a Group of People

In this paper we address robot-human interactions in a multi-robot and people group framework. The objective is to develop and evaluate techniques for missions in which several robots cooperate among themselves, interacting with a group of people. The robots detect people behaviors and act consequently adopting different strategies. Probabilistic techniques for robust cooperative detection of group and individual behavior are developed from the range finder information. Environment perception and cooperative motion planning techniques adaptable to the situation observed are developed and jointly used with the reactions to the people's behavior. In order to evaluate the system, we propose a scenario where the robots guide a group of people to a goal position. This scenario has been tested in simulations and in real experiments, to validate the techniques developed.