Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Hande Çelikkanat, Güner Orhan, Nicolas Pugeault, Frank Guerin, Erol Şahin, Sinan Kalkan

Research output: Contribution to journalArticle

Abstract

In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that: 1) it does not relearn everything from scratch given new interactions (i.e., it is online); and 2) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online, and robust: it is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.
Original languageEnglish
Pages (from-to)42-59
Number of pages18
JournalIEEE Transactions on Cognitive and Developmental Systems
Volume8
Issue number1
DOIs
Publication statusPublished - Mar 2016

Fingerprint

Robots
Computational linguistics
Object recognition
Planning

Cite this

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation. / Çelikkanat, Hande; Orhan, Güner; Pugeault, Nicolas; Guerin, Frank; Şahin, Erol; Kalkan, Sinan.

In: IEEE Transactions on Cognitive and Developmental Systems, Vol. 8, No. 1, 03.2016, p. 42-59.

Research output: Contribution to journalArticle

Çelikkanat, Hande ; Orhan, Güner ; Pugeault, Nicolas ; Guerin, Frank ; Şahin, Erol ; Kalkan, Sinan. / Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation. In: IEEE Transactions on Cognitive and Developmental Systems. 2016 ; Vol. 8, No. 1. pp. 42-59.
@article{e7f67e229c2e4beeb4e928892e255adb,
title = "Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation",
abstract = "In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that: 1) it does not relearn everything from scratch given new interactions (i.e., it is online); and 2) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online, and robust: it is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.",
author = "Hande {\cC}elikkanat and G{\"u}ner Orhan and Nicolas Pugeault and Frank Guerin and Erol Şahin and Sinan Kalkan",
year = "2016",
month = "3",
doi = "10.1109/TAMD.2015.2476374",
language = "English",
volume = "8",
pages = "42--59",
journal = "IEEE Transactions on Cognitive and Developmental Systems",
issn = "2379-8920",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

AU - Çelikkanat, Hande

AU - Orhan, Güner

AU - Pugeault, Nicolas

AU - Guerin, Frank

AU - Şahin, Erol

AU - Kalkan, Sinan

PY - 2016/3

Y1 - 2016/3

N2 - In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that: 1) it does not relearn everything from scratch given new interactions (i.e., it is online); and 2) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online, and robust: it is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.

AB - In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that: 1) it does not relearn everything from scratch given new interactions (i.e., it is online); and 2) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online, and robust: it is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.

U2 - 10.1109/TAMD.2015.2476374

DO - 10.1109/TAMD.2015.2476374

M3 - Article

VL - 8

SP - 42

EP - 59

JO - IEEE Transactions on Cognitive and Developmental Systems

JF - IEEE Transactions on Cognitive and Developmental Systems

SN - 2379-8920

IS - 1

ER -