Probabilistic Grammars for Plan Recognition
نویسندگان
چکیده
thenis Teneketzis for their many comments and suggestions on this dissertation. Thanks also to all of the members of the Decision Machine Group for all of their feedback at various stages of the research. Thanks to my various ooce-mates over the years for not overly straining our limited computing resources, and special thanks to Daniel Berwick for providing his stereo system to enhance the research environment. And very special thanks go to Prof. Michael P. Wellman as my research advisor, co-author, etc. for all of his ideas, words, and timely nodding.
منابع مشابه
Probabilistic State-Dependent Grammars for Plan Recognition
Techniques for plan recognition under uncertainty require a stochastic model of the plangeneration process. We introduce probabilistic state-dependent grammars (PSDGs) to represent an agent’s plan-generation process. The PSDG language model extends probabilistic contextfree grammars (PCFGs) by allowing production probabilities to depend on an explicit model of the planning agent’s internal and ...
متن کاملString Shuffling over a Gap between Parsing and Plan Recognition
We propose a new probabilistic plan recognition algorithm YR based on an extension of Tomita’s Generalized LR (GLR) parser for grammars enriched with the shuffle operator. YR significantly outperforms previous approaches based on topdown parsers, shows more consistent run times among similar libraries, and degrades more gracefully as plan library complexity increases. YR also lifts the restrict...
متن کاملFixing a Hole in Lexicalized Plan Recognition
Previous work has suggested the use of lexicalized grammars for probabilistic plan recognition. Such grammars allow the domain builder to delay commitment to hypothesizing high level goals in order to reduce computational costs. However this delay has limitations. In the case of only partial observation traces, delaying commitment can prevent such algorithms from forming correct conclusions abo...
متن کاملLexical Ambiguity and its Impact on Plan Recognition for Intrusion Detection
Viewing intrusion detection as a problem of plan recognition presents unique problems. Real world security domains are highly ambiguous and this creates significant problems for plan recognition. This paper distinguishes three sources of ambiguity: action ambiguity, syntactic ambiguity and attachment ambiguity. Previous work in plan recognition has often conflated these different sources of amb...
متن کاملA probabilistic plan recognition algorithm based on plan tree grammars
We present the PHATT algorithm for plan recognition. Unlike previous approaches to plan recognition, PHATT is based on a model of plan execution. We show that this clarifies several difficult issues in plan recognition including the execution of multiple interleaved root goals, partially ordered plans, and failing to observe actions. We present the PHATT algorithm’s theoretical basis, and an im...
متن کاملConsidering State in Plan Recognition with Lexicalized Grammars
This paper documents extending the ELEXIR (Engine for LEXicalized Intent Recognition) system (Geib 2009; Geib and Goldman 2011) with a world model. This is a significant increase in the expressiveness of the plan recognition system and allows a number of additions to the algorithm, most significantly conditioning probabilities for recognized plans on the state of the world during execution. Sin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999