Challenges in Building Very Large Teams

Paul Scerri (), Yang Xu (), Jumpol Polvichai (), Bin Yu (), Steven Okamoto (), Mike Lewis () and Katia Sycara ()
Additional contact information
Paul Scerri: Carnegie Mellon University
Yang Xu: University of Pittsburgh
Jumpol Polvichai: University of Pittsburgh
Bin Yu: Carnegie Mellon University
Steven Okamoto: Carnegie Mellon University
Mike Lewis: University of Pittsburgh
Katia Sycara: Carnegie Mellon University

A chapter in Cooperative Systems, 2007, pp 197-228 from Springer

Abstract: Summary Coordination of large numbers of unmanned aerial vehicles is difficult due to the limited communication bandwidth available to maintain cohesive activity in a dynamic, often hostile and unpredictable environment. We have developed an integrated coordination algorithm based on the movement of tokens around a network of vehicles. Possession of a token represents exclusive access to the task or resource represented by the token or exclusive ability to propagate the information represented by the token. The movement of tokens is governed by a local decision theoretic model that determines what to do with the tokens in order to maximize expected utility. The result is effective coordination between large numbers of UAVs with very little communication. However, the overall movement of tokens can be very complex and, since it relies on heuristics, configuration parameters need to be tuned for a specific scenario or preferences. We have developed a neural network model of the relationship between configuration and environment parameters and performance, that an operator uses to rapidly configure a team or even reconfigure the team online, as the environment changes.

Keywords: Joint Activity; Multiagent System; Unmanned Aerial Vehicle; Autonomous Agent; Task Allocation (search for similar items in EconPapers)
Date: 2007
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnechp:978-3-540-48271-0_13

Ordering information: This item can be ordered from
http://www.springer.com/9783540482710

DOI: 10.1007/978-3-540-48271-0_13

Access Statistics for this chapter

More chapters in Lecture Notes in Economics and Mathematical Systems from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().