Neuro-fuzzy based adaptive co-operative mobile robots

This paper focuses on the development of intelligent multi-agent robot teams that are capable of acting autonomously and of collaborating in a dynamic environment to achieve team objectives. Fuzzy and neuro-fuzzy based mechanisms are proposed that enable these robots automatically to generate co-operative behaviours and to adapt their performance during the specified time of the mission. These abilities are important because of uncertainty in the environmental conditions and because of possible functional failures in some team members. The improvement in team performance is achieved by updating the control parameters of the robots based on knowledge acquired on-line. These techniques are applied to a simulated team of mobile robots performing two different proof-of-concept tasks: dynamic target tracking and co-operative box pushing, The results show that the robot team is able to achieve adaptive cooperative control despite dynamic changes in the environment and variation in the capabilities of the team members.