Multi-Agent Plan Recognition (MAPR) aims to recognize dynamic team structures and team behaviors from the observed team traces (activity sequences) of a set of intelligent agents. Previous MAPR approaches required a library of team activity sequences (team plans) be given as input. However, collecting a library of team plans to ensure adequate coverage is often difficult and costly. In this paper, we relax this constraint, so that team plans are not required to be provided beforehand. We assume instead that a set of action models are available.

Multi-Agent Plan Recognition (MAPR) aims to recognize dynamic team structures and team behaviors from the observed team traces (activity sequences) of a set of intelligent agents. Previous MAPR approaches required a library of team activity sequences (team plans) be given as input. However, collecting a library of team plans to ensure adequate coverage is often difficult and costly. In this paper, we relax this constraint, so that team plans are not required to be provided beforehand. We assume instead that a set of action models are available. Such models are often already created to describe domain physics; i.e., the preconditions and effects of effects actions. We propose a novel approach for recognizing multi-agent team plans based on such action models rather than libraries of team plans. We encode the resulting MAPR problem as a \emph{satisfiability problem} and solve the problem using a state-of-the-art weighted MAX-SAT solver. Our approach also allows for incompleteness in the observed plan traces. Our empirical studies demonstrate that our algorithm is both effective and efficient in comparison to state-of-the-art MAPR methods based on plan libraries.

Multi-Agent Plan Recognition (MAPR) seeks to proposed to formalize MAPR with a new model, revealing identify the dynamic team structures and team behaviors the distinction between the hardness of single and multi-agent from the observed activity sequences (team plan recognition, and solve MAPR problems in the model using traces) of a set of intelligent agents, based on a a first-cut approach, provided that a fully observed team library of known team activity sequences (team trace and a library of full team plans were given as input plans). Previous MAPR systems require that team [Banerjee et al., 2010]; etc. traces and team plans are fully observed. In this Despite the success of previous approaches, they either assume paper we relax this constraint, i.e., team traces and that agents in the same team can only execute a common team plans are allowed to be partial. This is an important activity, i.e., coordinated activities of agents are not allowed task in applying MAPR to real-world domains, in a team, or require that the team trace and team plans are since in many applications it is often difficult complete, i.e., missing values (activities that are missing) are to collect full team traces or team plans due not allowed. In many real-world applications, however, it is to environment limitations, e.g., military operation.