Fast and Complete Symbolic Plan Recognition

Dorit Avrahami-Zilberbrand, Gal A. Kaminka

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent applications of plan recognition face several open challenges: (i) matching observations to the plan library is costly, especially with complex multi-featured observations; (ii) computing recognition hypotheses is expensive. We present techniques for addressing these challenges. First, we show a novel application of machine-learning decision-tree to efficiently map multi-featured observations to matching plan steps. Second, we provide efficient lazy-commitment recognition algorithms that avoid enumerating hypotheses with every observation, instead only carrying out bookkeeping incrementally. The algorithms answer queries as to the current state of the agent, as well as its history of selected states. We provide empirical results demonstrating their efficiency and capabilities
Original languageAmerican English
Title of host publicationIJCAI
StatePublished - 2005

Bibliographical note

Place of conference:SCOTLAND

Fingerprint

Dive into the research topics of 'Fast and Complete Symbolic Plan Recognition'. Together they form a unique fingerprint.

Cite this