Multiagent Plan Recognition from Partially Observed Team Traces
Hankz Hankui Zhuo, Sun Yat-sen University, Guangzhou, China
Multiagent plan recognition (MAPR) aims to recognize team structures and team behaviors from the observed team traces (action sequences) of a set of intelligent agents. This chapter introduces the problem formulation of MAPR based on partially observed team traces and presents a weighted MAX-SAT-based framework to recognize multiagent plans from partially observed team traces. This framework spans two approaches, MARS (MultiAgent plan Recognition System) and DARE (Domain model-based multiAgent REcognition), with respect to different input knowledge. MARS requires as input a plan library, while DARE ...