Towards flexible teamwork (1997)
Cached
Download Links
- [teamcore.usc.edu:8080]
- [teamcore.usc.edu]
- [www.isi.edu]
- [arxiv.org]
- DBLP
Other Repositories/Bibliography
| Venue: | JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH |
| Citations: | 569 - 57 self |
BibTeX
@ARTICLE{Tambe97towardsflexible,
author = {Milind Tambe},
title = {Towards flexible teamwork},
journal = {JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH},
year = {1997},
volume = {7},
pages = {83--124}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Many AI researchers are today striving to build agent teams for complex, dynamic multi-agent domains, with intended applications in arenas such as education, training, entertainment, information integration, and collective robotics. Unfortunately, uncertainties in these complex, dynamic domains obstruct coherent teamwork. In particular, team members often encounter differing, incomplete, and possibly inconsistent views of their environment. Furthermore, team members can unexpectedly fail in fulfilling responsibilities or discover unexpected opportunities. Highly flexible coordination and communication is key in addressing such uncertainties. Simply tting individual agents with precomputed coordination plans will not do, for their in flexibility can cause severe failures in teamwork, and their domain-specificity hinders reusability. Our central hypothesis is that the key to such flexibility and reusability isproviding agents with general models of teamwork. Agents exploit such models to autonomously reason about coordination and communication, providing requisite flexibility. Furthermore, the models enable reuse across domains, both saving implementation effort and enforcing consistency. This article presents one general, implemented model of teamwork, called STEAM. The basic building block of teamwork in STEAM is joint intentions (Cohen & Levesque, 1991b); teamwork in STEAM is based on agents' building up a (partial) hierarchy of joint intentions (this hierarchy is seen to parallel Grosz & Kraus's partial Shared-Plans, 1996). Furthermore, in STEAM, team members monitor the team's and individual members' performance, reorganizing the team as necessary. Finally, decision-theoretic communication selectivity in STEAM ensures reduction in communication overheads of teamwork, with appropriate sensitivity to the environmental conditions. This article describes STEAM's application in three different complex domains, and presents detailed empirical results.
Keyphrases
team member towards flexible teamwork joint intention grosz kraus environmental condition communication overhead cohen levesque collective robotics many ai researcher coherent teamwork individual member requisite flexibility highly flexible coordination individual agent domain-specificity hinders reusability dynamic domain basic building block partial shared-plans decision-theoretic communication selectivity agent team different complex domain appropriate sensitivity severe failure dynamic multi-agent domain implementation effort general model present detailed empirical result inconsistent view information integration central hypothesis discover unexpected opportunity precomputed coordination plan
