This chapter describes a novel method for incremental intention recognition. It is performed and achieved by incrementally constructing a three layer Bayesian Network model as more actions are observed. The Bayesian Network is composed from a knowledge base of readily specified and readily maintained Bayesian Network fragments. Their simple structures allow easy maintenance by domain experts and also facilitate automatic construction from available plan corpora. Improved performance of the method on the Linux plan corpus case is exhibited.
|Number of pages
|Studies in Applied Philosophy, Epistemology and Rational Ethics
|Published - 1 Jan 2013