Automatic Task Selection from Targets Recognition for Swarm Mobile Robots with Specialized Agents

摘要

Considering specialized agents in swarm robotics, with robots dedicated to specific tasks, requires that formation control and efficient transition in the leadership of the swarm is achieved. Here, a task switching approach is formulated by evolving the definition of specialization to match with targets recognition in the environment, such as detecting special landmarks via embedded sensors. Specialization zones are defined around each detected target corresponding to a task to be dealt with by a specific robot. Entering within the zone of influence surrounding a target triggers the switching of the leader of the formation. The framework is also further refined by making the targets, and therefore the corresponding zone of influence, dynamic, which leads to the consideration of combined specialization areas. The proposed system is validated in simulation to demonstrate that the group of robots effectively coordinate themselves around targets and dynamically allocate the appropriate specialized agent.