Interactive Human-Robot Pole Balancing Utilizing Multiple Virtual Fuzzy Agents

A new intelligent controller based on multiple virtual agents is presented in this paper. The controller is used to produce appropriate actions for a robot interacting with a human in performing specific tasks. The virtual agents monitor the robot and its environment (including the human) and propose actions. Associated with each proposal is three evaluation measures, quantified to allow selection of the proper action. These assay characteristics are relevance, confidence, and effect. The intelligent agents are based on fuzzy logic controllers. The agents cooperate for the robot to function properly, while at the same time compete to take control of the robot. It is the simultaneous cooperation and competition of the virtual agents that is the foundation of the proposed novel system controller. The functionality of the system controller is demonstrated through the interactive simulated task of pole balancing between a human and a robot.

[1]  Susan Hackwood,et al.  Self-organization of sensors for swarm intelligence , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[2]  A. H. Levis,et al.  Distributed Intelligence Systems , 1992 .

[3]  Yuichiro Anzai.  Human-robot-computer interaction: a new paradigm of research in robotics , 1993, Adv. Robotics.

[4]  Hajime Asama,et al.  Collaborative team organization using communication in a decentralized robotic system , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[5]  Kanya Tanaka,et al.  Mechanical impedance characteristics of robots for coexistence with humans , 1995, Proceedings 4th IEEE International Workshop on Robot and Human Communication.

[6]  Arvin Agah,et al.  A genetic algorithm-based controller for decentralized multi-agent robotic systems , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[7]  Ryojun Ikeura,et al.  Cooperative motion control of a robot and a human , 1994, Proceedings of 1994 3rd IEEE International Workshop on Robot and Human Communication.

[8]  K. Yokota,et al.  A human interface system for the multi-agent robotic system , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[9]  F. Arai,et al.  Control Strategies for Cellular Robotic Network , 1991 .

[10]  Yasushi Nakauchi,et al.  Multi-agent interface architecture for human-robot cooperation , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.