The investigation of the concept of a multiagent plan-recognition model to assist the tactical decision-maker in interpreting the activity of enemy platforms and predicting their goals and plans is discussed. A previously developed single-agent plant-recognition model has been extended to create a prototype multiagent model. Dependencies among the agents, motivations underlying their goals, and the context in which the activity unfolds are captured within the model. Activation of the plan-recognition process has been made more opportunistic through the use of critical discriminators. The issue of adversarial agents interacting in a dynamically changing world has been addressed by means of a two-sided differential game technique.
Multiagent plan recognition in an adversarial domain
Mehrfaktoren Planerkennung im gegnerischen Bereich
1987
6 Seiten, 12 Quellen
Conference paper
English
Multiagent modeling of pedestrian-vehicle conflicts using Adversarial Inverse Reinforcement Learning
Taylor & Francis Verlag | 2023
|Adversarial Semi-supervised Multi-domain Tracking
British Library Conference Proceedings | 2021
|Multiagent Coordination Strategies
Wiley | 2012
|Distributed Multiagent Systems
Springer Verlag | 2022
|