Placing objects with multiple mobile robots-mutual help using intention inference

This paper presents a behavior-decision method using intention inference to facilitate cooperation among multiple mobile robots. The robots infer the intentions of other robots by observing their behaviors to settle conflicts and to cooperate in accomplishing tasks. If the inference rules used by the robots are made similar to the rules human use, this approach can be applied to cooperation between humans and robots. The intention inference method is tested with an objects placement problem. In this test, the robots share tasks, push objects cooperatively, and avoid collision with others. They can cope with dynamic and uncertain environments because this method allows for flexible decision-making. Simulated and experimental results indicate the method's feasibility.