Gal A. Kaminka's Publications

Sorted by DateClassified by Publication TypeClassified by TopicGrouped by Student (current)Grouped by Former Students

Plan Recognition in Continuous Domains

Gal A. Kaminka, Mor Vered, and Noa Agmon. Plan Recognition in Continuous Domains. In Proceedings of the AAAI Conference on Artificial Intelligence , 2018. An earlier version was published in the IJCAI 2017 workshop on Goal Reasoning.

Download

[PDF]598.6kB  

Abstract

Plan recognition is the task of inferring the plan of an agent, basedon an incomplete sequence of its observed actions. Previous formulations of plan recognition commit early to discretizations of the environment and the observed agent's actions. This leads to reduced recognition accuracy.To address this, we first provide a formalization of recognitionproblems which admits continuous environments, as well as discrete domains.We then show that through mirroring---generalizing plan-recognition by planning---wecan apply continuous-world motion planners in plan recognition. We provide formal arguments for the usefulness of mirroring, and empirically evaluate mirroring in more than a thousand recognition problemsin three continuous domains and six classical planning domains.

Additional Information

BibTeX

@inproceedings{aaai18,
	author = {Gal A. Kaminka and Mor Vered and Noa Agmon},
title = {Plan Recognition in Continuous Domains},
booktitle = AAAI,
OPTcrossref = {crossref},
OPTkey = {key},
OPTpages = {pages},
year = {2018},
OPTeditor = {editor},
OPTvolume = {volume},
OPTnumber = {number},
OPTseries = {series},
OPTaddress = {address},
OPTmonth = {month},
OPTorganization = {organization},
OPTpublisher = {publisher},
note = {An earlier version was published in the IJCAI 2017 workshop on Goal Reasoning.},
OPTannote = {annote},
wwwnote = {}, 
OPTkeywords = {},
abstract = {
Plan  recognition is the task of inferring the  plan of an agent, based
on an incomplete sequence of its observed actions. Previous formulations of plan recognition commit early to discretizations of the environment and the observed 
agent's actions. This leads to reduced recognition accuracy.
To address this, we first provide a formalization of recognition
problems which admits continuous environments, as well as discrete domains.
We then show that through \textit{mirroring}---generalizing plan-recognition by planning---we
can apply continuous-world motion planners in plan recognition.  We provide formal arguments 
for the usefulness of mirroring, and empirically evaluate 
mirroring  in more than a thousand recognition problems
in three continuous domains and six classical planning domains.
},	
}

Generated by bib2html.pl (written by Patrick Riley ) on Sat Feb 24, 2018 00:31:02