ABSTRACT
SUMMARY This chapter presents the development of an intelligent multi-robot system. Robots in a multi-robot system coordinate and cooperate with each other when they accomplish global tasks. In this chapter, we present a system that is fully autonomous, distributed, and fault-tolerant. The system autonomously decides the appropriate number of suitable and most capable robots in the team to cooperate with each other in carrying out a global task while resolving partial or full failures of the robots during the execution of the task. In our system, the strategies of communication, coordination, and cooperation are based on the principles of human immune systems and the modified model of Jerne’s idiotypic network theory. A genetic algorithm is used to optimize the binding affinity function that is needed for selection of the most appropriate robot in a fleet to cooperate with the robot that solicits help. The feasibility of the scheme is demonstrated by implementing the system in a team of simulated heterogeneous mobile robots that cooperatively transport multiple objects to a goal location.
