Landmark-enhanced heuristics for goal recognition in incomplete domain models

Ramon Fraga Pereira; André Grahl Pereira; Felipe Meneguzzi

Landmark-enhanced heuristics for goal recognition in incomplete domain models

Ramon Fraga Pereira, André Grahl Pereira, Felipe Meneguzzi

Computing Science

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

8 Citations (Scopus)

Abstract

Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume completeness and correctness of the domain theory against which their algorithms match observations: this is too strong for most real-world domains. In this paper, we develop goal recognition techniques that are capable of recognizing goals using incomplete domain theories by considering different notions of planning landmarks in such domains. We evaluate the resulting techniques empirically in a large dataset of incomplete domains, and perform an ablation study to understand their effect on recognition performance.

Original language	English
Title of host publication	Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019
Editors	J. Benton, Nir Lipovetzky, Eva Onaindia, David E. Smith, Siddharth Srivastava
Publisher	AAAI Press
Pages	329-337
Number of pages	9
ISBN (Electronic)	9781577358077
Publication status	Published - 2019
Event	29th International Conference on Automated Planning and Scheduling, ICAPS 2019 - Berkeley, United States Duration: 11 Jul 2019 → 15 Jul 2019

Conference

Conference	29th International Conference on Automated Planning and Scheduling, ICAPS 2019
Country/Territory	United States
City	Berkeley
Period	11/07/19 → 15/07/19

Cite this

Landmark-enhanced heuristics for goal recognition in incomplete domain models. / Pereira, Ramon Fraga; Pereira, André Grahl; Meneguzzi, Felipe.

Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. ed. / J. Benton; Nir Lipovetzky; Eva Onaindia; David E. Smith; Siddharth Srivastava. AAAI Press, 2019. p. 329-337.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Pereira, RF, Pereira, AG & Meneguzzi, F 2019, Landmark-enhanced heuristics for goal recognition in incomplete domain models. in J Benton, N Lipovetzky, E Onaindia, DE Smith & S Srivastava (eds), Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. AAAI Press, pp. 329-337, 29th International Conference on Automated Planning and Scheduling, ICAPS 2019, Berkeley, United States, 11/07/19.

@inproceedings{4aeedab2a66b4069b0f0f9608d60c28f,

title = "Landmark-enhanced heuristics for goal recognition in incomplete domain models",

abstract = "Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume completeness and correctness of the domain theory against which their algorithms match observations: this is too strong for most real-world domains. In this paper, we develop goal recognition techniques that are capable of recognizing goals using incomplete domain theories by considering different notions of planning landmarks in such domains. We evaluate the resulting techniques empirically in a large dataset of incomplete domains, and perform an ablation study to understand their effect on recognition performance.",

author = "Pereira, {Ramon Fraga} and Pereira, {Andr{\'e} Grahl} and Felipe Meneguzzi",

note = "Funding Information: We thank Miquel Ram{\'i}rez for the invaluable discussions about previous versions of this paper. This study was financed in part by the Coordena{\c c}{\~a}o de Aperfei{\c c}oamento de Pessoal de Nivel Superior - Brasil (CAPES) - Finance Code 001. Felipe acknowledges support from CNPq under project numbers 407058/2018-4 and 305969/2016-1. Publisher Copyright: {\textcopyright} 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 29th International Conference on Automated Planning and Scheduling, ICAPS 2019 ; Conference date: 11-07-2019 Through 15-07-2019",

year = "2019",

language = "English",

pages = "329--337",

editor = "J. Benton and Nir Lipovetzky and Eva Onaindia and Smith, {David E.} and Siddharth Srivastava",

booktitle = "Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019",

publisher = "AAAI Press",

}

TY - GEN

T1 - Landmark-enhanced heuristics for goal recognition in incomplete domain models

AU - Pereira, Ramon Fraga

AU - Pereira, André Grahl

AU - Meneguzzi, Felipe

N1 - Funding Information: We thank Miquel Ramírez for the invaluable discussions about previous versions of this paper. This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior - Brasil (CAPES) - Finance Code 001. Felipe acknowledges support from CNPq under project numbers 407058/2018-4 and 305969/2016-1. Publisher Copyright: © 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

PY - 2019

Y1 - 2019

N2 - Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume completeness and correctness of the domain theory against which their algorithms match observations: this is too strong for most real-world domains. In this paper, we develop goal recognition techniques that are capable of recognizing goals using incomplete domain theories by considering different notions of planning landmarks in such domains. We evaluate the resulting techniques empirically in a large dataset of incomplete domains, and perform an ablation study to understand their effect on recognition performance.

AB - Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume completeness and correctness of the domain theory against which their algorithms match observations: this is too strong for most real-world domains. In this paper, we develop goal recognition techniques that are capable of recognizing goals using incomplete domain theories by considering different notions of planning landmarks in such domains. We evaluate the resulting techniques empirically in a large dataset of incomplete domains, and perform an ablation study to understand their effect on recognition performance.

UR - http://www.scopus.com/inward/record.url?scp=85079483784&partnerID=8YFLogxK

M3 - Published conference contribution

AN - SCOPUS:85079483784

SP - 329

EP - 337

BT - Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019

A2 - Benton, J.

A2 - Lipovetzky, Nir

A2 - Onaindia, Eva

A2 - Smith, David E.

A2 - Srivastava, Siddharth

PB - AAAI Press

T2 - 29th International Conference on Automated Planning and Scheduling, ICAPS 2019

Y2 - 11 July 2019 through 15 July 2019

ER -

Landmark-enhanced heuristics for goal recognition in incomplete domain models

Abstract

Conference

Other files and links

Fingerprint

Cite this