Evolution of the GPGP/TÆMS domain-independent coordination framework

  • Authors:
  • Victor R. Lesser

  • Affiliations:
  • University of Massachusetts/Amherst

  • Venue:
  • Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

Generalized Partial Global Planning (GPGP) and its associated TÆMS hierarchical task network representation were developed as a domain-independent framework for coordinating the real-time activities of small teams of cooperative agents working to achieve a set of high-level goals. GPGP's development was influenced by two factors: one was to generalize and make domain-independent the coordination techniques developed in the Partial Global Planning (PGP) framework (this also involved our understanding that coordination activities could be separated from local agent control if an appropriate bi-directional interface could be established between them); the other was based on viewing agent coordination in terms of coordinating a distributed search of a dynamically evolving goal tree. Underlying these two influences was a desire to construct a model that could be used to explain and motivate the reasons for coordination among agents based on a quantitative view of task/subproblem dependency. Coordination of behaviors among agents requires three things: specification (creating shared goals), planning (subdividing goals into subgoals/tasks, i.e., creating the substructure of the evolving goal tree) and scheduling (assigning tasks to individual agents or groups of agents, creating shared plans and schedules and allocating resources). GPGP is primarily concerned with scheduling activities rather than the dynamic specification and planning of evolving activities (e.g., such as decomposing a high-level goal into a set of subgoals that if successfully achieved will solve the high-level goals).