A multi-agent system for executing group tasks

5Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.
Get full text

Abstract

We have developed a multi-agent system to support the robust execution of group tasks by simulated vehicles or future unmanned systems. The system supports the dynamic creation of new groups for a specific task, using a co-ordination strategy appropriate for the task. The system includes a specialised user agent that provides an interface to a human controller. The user treats the system as providing a 'pool' of capabilities that can be tasked to achieve the user's goals. The user may specify multi-phase missions that the system must attempt to complete and additionally can direct the system to undertake extra tasks that may remove assets from the main mission. The group plan execution framework allows the agents to re-organise to match the user's requests.

Cite

CITATION STYLE

APA

Baxter, J. W., & Horn, G. S. (2003). A multi-agent system for executing group tasks. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2774 PART 2, pp. 697–703). Springer Verlag. https://doi.org/10.1007/978-3-540-45226-3_96

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free