Team-Oriented Agent Coordination in the RETSINA Multi-Agent System

Abstract

Complex tasks are often solved by teams because no one individual has the collective expertise, information, or resources required for the effective completion or performance of a task. This paper describes a prototype, implemented in the RETSINA multi-agent infrastructure, in which agents interact with each other via capability-based and team-oriented coordination. We propose a model of team-oriented agent coordination that is based on the joint intentions theory, so that agents can communicate their intended commitments to each other. Team-oriented agents communicate partial descriptions of the context in which a mission must be executed and the resources to do so via data structures that are analogous to the SharedPlans recipe. The agents then proceed, in a process reminiscent of SharedPlans partial plan refinement,to refine and revise their understanding of the mission context, via both team-oriented and capability-based coordination with other RETSINA agents, while executing their mission. The partial plan refinement behavior is made possible through the RETSINA Agent Architecture, which interleaves HTN planning and process execution. We enhance the above models of teamwork by adding our own characterizations of checkpoints, role and subgoal relations in software agent teamwork, and show how the software agents can acquire this information from their operating environment during plan execution time. Such enhancements create a scalable team-oriented multi-agent system architecture, in which team coordination strategies can be implemented in a general and domain-independent way.