RESC: An Approach for Real-time, Dynamic Agent Tracking

Abstract

Agent tracking involves monitoring the observable actions of other agents as well as inferring their unobserved actions, plans, goals and behaviors. In a dynamic, real-time environment, an intelligent agent faces the challenge of tracking other agents' flexible mix of goaldriven and reactive behaviors, and doing so in real-time, despite ambiguities. This paper presents RESC (REal-time Situated Commitments), an approach that enables an intelligent agent to meet this challenge. RESC's situatedness derives from its constant uninterrupted attention to the current world situation - it always tracks other agents' on-going actions in the context of this situation. Despite ambiguities, RESC quickly commits to a single interpretation of the on-going actions (without an extensive examination of the alternatives), and uses that in service of interpretation of future actions. However, should its commitments lead to inconsistencies in tracking, it uses singlestate backtracking to undo some of the commitments and repair the inconsistencies. Together, RESC's situatedness, immediate commitment, and single-state backtracking conspire in providing RESC its real-time character. RESC is implemented in the context of intelligent pilot agents participating in a real-world synthetic air-combat environment. Experimental results illustrating RESC's effectiveness are presented.