Lifelong Adaptation in Heterogeneous Multi-Robot Teams: Response to Continual Variation in Individual Robot Performance

Generating teams of robots that are able to perform their tasks over long periods of time requires the robots to be responsive to continual changes in robot team member capabilities and to changes in the state of the environment and mission. In this article, we describe the L-ALLIANCE architecture, which enables teams of heterogeneous robots to dynamically adapt their actions over time. This architecture, which is an extension of our earlier work on ALLIANCE, is a distributed, behavior-based architecture aimed for use in applications consisting of a collection of independent tasks. The key issue addressed in L-ALLIANCE is the determination of which tasks robots should select to perform during their mission, even when multiple robots with heterogeneous, continually changing capabilities are present on the team. In this approach, robots monitor the performance of their teammates performing common tasks, and evaluate their performance based upon the time of task completion. Robots then use this information throughout the lifetime of their mission to automatically update their control parameters. After describing the L-ALLIANCE architecture, we discuss the results of implementing this approach on a physical team of heterogeneous robots performing proof-of-concept box pushing experiments. The results illustrate the ability of L-ALLIANCE to enable lifelong adaptation of heterogeneous robot teams to continuing changes in the robot team member capabilities and in the environment.

[1]  Manuela M. Veloso,et al.  Layered Approach to Learning Client Behaviors in the Robocup Soccer Server , 1998, Appl. Artif. Intell..

[2]  Randall Davis,et al.  Negotiation as a Metaphor for Distributed Problem Solving , 1988, Artificial Intelligence.

[3]  Edmund H. Durfee,et al.  A Hierarchical Protocol for Coordinating Mulitagent Behaviors , 1990, AAAI.

[4]  Lynne E. Parker.  Distributed control of multi-robot teams: Cooperative baton passing task , 1998 .

[5]  Claus Ronald. Kube,et al.  Collective robotic intelligence , 1992 .

[6]  Reid G. Smith,et al.  The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver , 1980, IEEE Transactions on Computers.

[7]  Lynne E. Parker,et al.  Case study for life-long learning and adaptation in coopertive robot teams , 1999, Optics East.

[8]  Guy Theraulaz,et al.  Task differentiation in Polistes wasp colonies: a model for self-organizing groups of robots , 1991 .

[9]  David S. Johnson,et al.  Computers and In stractability: A Guide to the Theory of NP-Completeness. W. H Freeman, San Fran , 1979 .

[10]  Yuichiro Anzai,et al.  LEMMING: A learning system for multi-robot environments , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[11]  Lynne E. Parker,et al.  Cooperative Robotics for Multi-Target Observation , 1999, Intell. Autom. Soft Comput..

[12]  Sandip Sen,et al.  Evolution and learning in multiagent systems , 1998, Int. J. Hum. Comput. Stud..

[13]  Alan H. Bond,et al.  Readings in Distributed Artificial Intelligence , 1988 .

[14]  Tucker R. Balch,et al.  Communication of behavorial state in multi-agent retrieval tasks , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[15]  Lynne E. Parker,et al.  On the design of behavior-based multi-robot teams , 1995, Adv. Robotics.

[16]  Lynne E. Parker,et al.  Heterogeneous multi-robot cooperation , 1994 .

[17]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[18]  Luc Steels,et al.  Cooperation between distributed agents through self-organisation , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[19]  Jing Wang,et al.  DRS operating primitives based on distributed mutual exclusion , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[20]  Jeffrey S. Rosenschein,et al.  Negotiation and Conflict Resolution in Non-Cooperative Domains , 1990, AAAI.

[21]  Lynne E. Parker,et al.  ALLIANCE: an architecture for fault tolerant multirobot cooperation , 1998, IEEE Trans. Robotics Autom..

[22]  Randall Steeb,et al.  Strategies of Cooperation in Distributed Problem Solving , 1983, IJCAI.

[23]  Sandip Sen,et al.  Learning to Coordinate without Sharing Information , 1994, AAAI.

[24]  Maja J. Matarić,et al.  Designing emergent behaviors: from local interactions to collective intelligence , 1993 .

[25]  Mark Yim,et al.  Indoor automation with many mobile robots , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[26]  Ming Tan,et al.  Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents , 1997, ICML.

[27]  Paul R. Cohen,et al.  Real-Time Problem Solving in The Phoenix Environment , 1990 .

[28]  Jeffrey S. Rosenschein,et al.  Deals Among Rational Agents , 1985, IJCAI.

[29]  Giulio Sandini,et al.  Self-organizing collection and transport of objects in unpredictable environments , 1990 .

[30]  Yaser Al-Onaizan,et al.  On being a teammate: experiences acquired in the design of RoboCup teams , 1999, AGENTS '99.

[31]  M. Benda,et al.  On Optimal Cooperation of Knowledge Sources , 1985 .

[32]  Hajime Asama,et al.  Development of Task Assignment System Using Communication for Multiple Autonomous Robots , 1992, J. Robotics Mechatronics.

[33]  Gerhard Weiß,et al.  Adaptation and Learning in Multi-Agent Systems: Some Remarks and a Bibliography , 1995, Adaption and Learning in Multi-Agent Systems.

[34]  Lynne E. Parker,et al.  Adaptive heterogeneous multi-robot teams , 1998, Neurocomputing.

[35]  Bruce Randall Donald,et al.  Towards a Theory of Information Invariants for Cooperating Autonomous Mobile Robots , 1993 .

[36]  Randall Davis,et al.  Frameworks for Cooperation in Distributed Problem Solving , 1988, IEEE Transactions on Systems, Man, and Cybernetics.

[37]  Sandip Sen,et al.  Evolving Beharioral Strategies in Predators and Prey , 1995, Adaption and Learning in Multi-Agent Systems.

[38]  Martin Nilsson,et al.  Cooperative multi-robot box-pushing , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[39]  Sandip Sen,et al.  Adaption and Learning in Multi-Agent Systems: Ijcai'95 Workshop, Montreal, Canada, August 21, 1995, Proceedings , 1996 .

[40]  Victor R. Lesser,et al.  The Distributed Vehicle Monitoring Testbed: A Tool for Investigating Distributed Problem Solving Networks , 1983, AI Mag..

[41]  Fabrice R. Noreils,et al.  Toward a Robot Architecture Integrating Cooperation between Mobile Robots: Application to Indoor Environment , 1993, Int. J. Robotics Res..

[42]  Jacques Ferber,et al.  From Tom Thumb to the Dockers: some experiments with foraging robots , 1993 .

[43]  Frederick Hayes-Roth,et al.  Distributed Intelligence for Air Fleet Control , 1981 .

[44]  John S. Bay,et al.  Toward the development of a material transport system using swarms of ant-like robots , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[45]  Sandip Sen,et al.  Adaption and Learning in Multi-Agent Systems , 1995, Lecture Notes in Computer Science.

[46]  Lynne E. Parker,et al.  L-ALLIANCE: Task-oriented multi-robot learning in behavior-based systems , 1996, Adv. Robotics.