Goal Recognition in Latent Space

Leonardo Amado; Ramon Fraga Pereira; Joao Aires; Mauricio Magnaguagno; Roger Granada; Felipe Meneguzzi

doi:10.1109/IJCNN.2018.8489653

Goal Recognition in Latent Space

Leonardo Amado, Ramon Fraga Pereira, Joao Aires, Mauricio Magnaguagno, Roger Granada, Felipe Meneguzzi

Computing Science

Pontifícia Universidade Católica do Rio Grande do Sul

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

32 Citations (Scopus)

Abstract

Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.

Original language	English
Title of host publication	2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509060146
DOIs	https://doi.org/10.1109/IJCNN.2018.8489653
Publication status	Published - 10 Oct 2018
Event	2018 International Joint Conference on Neural Networks, IJCNN 2018 - Rio de Janeiro, Brazil Duration: 8 Jul 2018 → 13 Jul 2018

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2018-July

Conference

Conference	2018 International Joint Conference on Neural Networks, IJCNN 2018
Country/Territory	Brazil
City	Rio de Janeiro
Period	8/07/18 → 13/07/18

Bibliographical note

Funding Information:
Felipe thanks CNPq for partial financial support under its PQ fellowship, grant number 305969/2016-1.

Publisher Copyright:
© 2018 IEEE.

Access to Document

10.1109/IJCNN.2018.8489653

Cite this

Amado, L., Pereira, R. F., Aires, J., Magnaguagno, M., Granada, R., & Meneguzzi, F. (2018). Goal Recognition in Latent Space. In 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings Article 8489653 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2018-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2018.8489653

Goal Recognition in Latent Space. / Amado, Leonardo; Pereira, Ramon Fraga; Aires, Joao et al.
2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. 8489653 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2018-July).

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

Amado, L, Pereira, RF, Aires, J, Magnaguagno, M, Granada, R & Meneguzzi, F 2018, Goal Recognition in Latent Space. in 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings., 8489653, Proceedings of the International Joint Conference on Neural Networks, vol. 2018-July, Institute of Electrical and Electronics Engineers Inc., 2018 International Joint Conference on Neural Networks, IJCNN 2018, Rio de Janeiro, Brazil, 8/07/18. https://doi.org/10.1109/IJCNN.2018.8489653

@inproceedings{6085b2194a77405bb1d3e3f0b12dab3b,

title = "Goal Recognition in Latent Space",

abstract = "Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.",

author = "Leonardo Amado and Pereira, {Ramon Fraga} and Joao Aires and Mauricio Magnaguagno and Roger Granada and Felipe Meneguzzi",

note = "Funding Information: Felipe thanks CNPq for partial financial support under its PQ fellowship, grant number 305969/2016-1. Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Joint Conference on Neural Networks, IJCNN 2018 ; Conference date: 08-07-2018 Through 13-07-2018",

year = "2018",

month = oct,

day = "10",

doi = "10.1109/IJCNN.2018.8489653",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings",

address = "United States",

}

TY - GEN

T1 - Goal Recognition in Latent Space

AU - Amado, Leonardo

AU - Pereira, Ramon Fraga

AU - Aires, Joao

AU - Magnaguagno, Mauricio

AU - Granada, Roger

AU - Meneguzzi, Felipe

PY - 2018/10/10

Y1 - 2018/10/10

N2 - Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.

AB - Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.

UR - http://www.scopus.com/inward/record.url?scp=85056490326&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2018.8489653

DO - 10.1109/IJCNN.2018.8489653

M3 - Published conference contribution

AN - SCOPUS:85056490326

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Joint Conference on Neural Networks, IJCNN 2018

Y2 - 8 July 2018 through 13 July 2018

ER -

Goal Recognition in Latent Space

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this