Show simple item record

Data-driven Metareasoning for Collaborative Autonomous Systems

dc.contributor.authorHerrmann, Jeffrey
dc.description.abstractWhen coordinating their actions to accomplish a mission, the agents in a multi-agent system may use a collaboration algorithm to determine which agent performs which task. This paper describes a novel data-driven metareasoning approach that generates a metareasoning policy that the agents can use whenever they must collaborate to assign tasks. This metareasoning approach collects data about the performance of the algorithms at many decision points and uses this data to train a set of surrogate models that can estimate the expected performance of different algorithms. This yields a metareasoning policy that, based on the current state of the system, estimated the algorithms’ expected performance and chose the best one. For a ship protection scenario, computational results show that one version of the metareasoning policy performed as well as the best component algorithm but required less computational effort. The proposed data-driven metareasoning approach could be a promising tool for developing policies to control multi-agent autonomous systems.en_US
dc.description.sponsorshipThis work was supported in part by the U.S. Naval Air Warfare Center-Aircraft Division.en_US
dc.subjectdistributed task allocationen_US
dc.subjectmultiagent systemen_US
dc.titleData-driven Metareasoning for Collaborative Autonomous Systemsen_US
dc.relation.isAvailableAtInstitute for Systems Researchen_us
dc.relation.isAvailableAtDigital Repository at the University of Marylanden_us
dc.relation.isAvailableAtUniversity of Maryland (College Park, MD)en_us

Files in this item


This item appears in the following Collection(s)

Show simple item record