A generic formal plan recognition theory
Guy Camilleri · 2003
Plan recognition is the task of inferring intentions (in terms of plans) from the actions or utterances of observed actors (Kautz, 1986). In this paper, we provide a new logical formalization of plan recognition, which allows us to clearly specify, validate and design the plan recognition process (useful in several domains such as: discourse understanding, human computer interaction, and so on). However, depending on the applications different recognition strategies are used (top-down, bottom-up, and so on). Therefore, to describe the possible strategies, we only chose to formalize the reasoning basic steps of plan recognition. Moreover, only the specific aspects of the recognition problem are formalized and fixed. Therefore, the other aspects can be determined to satisfy the system needs. To illustrate our formalism, we describe two strategies of plan recognition used in many applications. We also present an algorithm useful to the discourse understanding.