Adaptive Teamwork Coordination Using Graph Matching over Hierarchical Intentional Structures

• Authors: Susannah Soon;Adrian Pearce;Max Noble
• Venue: AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
• Year: 2004

Many existing teamwork coordination approaches recognise team intention by using communications, and/or by identifying plan execution through observing agent actions. However, problems may arise when such information is unavailable, or when agents are not observable at runtime. This paper presents a new agent coordination strategy, called Rolegraphs, that represents and recognises team intentions without requiring full knowledge of plans, or complete observations. The strategy relies on the role relationships formed within hierarchical teamwork structures. A graph matching approach is used to interpret these hierarchical structures, and to recognise team intentions at runtime. The main contribution of this work is the use of efficient graph matching techniques to dynamically coordinate diverse and large-scale teams, where communications, observations, or plan details are incomplete. The Rolegraph coordination strategy is shown to be compatible with existing coordination approaches in the literature, and promises to improve the flexibility and robustness of coordination.