Recovery from Referent Misidentification in Systems of Communicating Agents

Shaohua Tang and Anthony S. Maida

When interacting autonomous agents operate in open domains that contain novel objects, the agents may not be able to refer to the objects by using preassigned names. As an alternative, the agents might use descriptions. When agents refer to domain objects by using descriptions, referent misidentifications will occur. This paper models recovery from referent misidentifications in systems of such agents.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.