Coordination-based cooperation protocol in multi-agent robotic systems

This paper proposes a coordination-based cooperation protocol for the object-sorting task in multi-agent robotic systems. The protocol coordinates the agents to move objects to destinations efficiently and effectively. Every agent autonomously makes subjective optimal decision, then the coordination algorithm resolves their conflicts by considering the global results. Since every agent runs the same algorithm to obtain the common results without further communication, the protocol is efficient. Implementation of the protocol is realized on a distributed modularized agent architecture. Experimental results shows that the protocol is effective and better than a previous proposed help-based protocol. In addition, its performance is very close to a high complexity model, genetic algorithms. The protocol can be applied to coordinate multiple autonomous robots for dispatching and transporting components in manufacturing systems.