Learning and using context on a humanoid robot using latent dirichlet allocation

Hande Celikkanat, Guner Orhan, Nicolas Pugeault, Frank Guerin, Erol Sahin, Sinan Kalkan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many relationships between objects and contexts, as well as between scenes and contexts.We use a concept web representation of the perceptions of the robot as a basis for context analysis. The detected contexts of the scene can be used for several cognitive problems. Our results demonstrate that the robot can use learned contexts to improve object recognition and planning.

Original languageEnglish
Title of host publication2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages201-207
Number of pages7
ISBN (Electronic)9781479975402
ISBN (Print)9781479975419
DOIs
Publication statusPublished - Dec 2014
Event4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014 - Genoa, Italy
Duration: 13 Oct 201416 Oct 2014

Conference

Conference4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014
CountryItaly
CityGenoa
Period13/10/1416/10/14

Fingerprint

Robots
Computational linguistics
Object recognition
Planning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Celikkanat, H., Orhan, G., Pugeault, N., Guerin, F., Sahin, E., & Kalkan, S. (2014). Learning and using context on a humanoid robot using latent dirichlet allocation. In 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob) (pp. 201-207). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEVLRN.2014.6982982

Learning and using context on a humanoid robot using latent dirichlet allocation. / Celikkanat, Hande; Orhan, Guner; Pugeault, Nicolas; Guerin, Frank; Sahin, Erol; Kalkan, Sinan.

2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob). Institute of Electrical and Electronics Engineers Inc., 2014. p. 201-207.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Celikkanat, H, Orhan, G, Pugeault, N, Guerin, F, Sahin, E & Kalkan, S 2014, Learning and using context on a humanoid robot using latent dirichlet allocation. in 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob). Institute of Electrical and Electronics Engineers Inc., pp. 201-207, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014, Genoa, Italy, 13/10/14. https://doi.org/10.1109/DEVLRN.2014.6982982
Celikkanat H, Orhan G, Pugeault N, Guerin F, Sahin E, Kalkan S. Learning and using context on a humanoid robot using latent dirichlet allocation. In 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob). Institute of Electrical and Electronics Engineers Inc. 2014. p. 201-207 https://doi.org/10.1109/DEVLRN.2014.6982982
Celikkanat, Hande ; Orhan, Guner ; Pugeault, Nicolas ; Guerin, Frank ; Sahin, Erol ; Kalkan, Sinan. / Learning and using context on a humanoid robot using latent dirichlet allocation. 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob). Institute of Electrical and Electronics Engineers Inc., 2014. pp. 201-207
@inproceedings{e1bf52ba9c434dadbd932db09101efb4,
title = "Learning and using context on a humanoid robot using latent dirichlet allocation",
abstract = "In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many relationships between objects and contexts, as well as between scenes and contexts.We use a concept web representation of the perceptions of the robot as a basis for context analysis. The detected contexts of the scene can be used for several cognitive problems. Our results demonstrate that the robot can use learned contexts to improve object recognition and planning.",
author = "Hande Celikkanat and Guner Orhan and Nicolas Pugeault and Frank Guerin and Erol Sahin and Sinan Kalkan",
note = "We would like to thank Angelo Cangelosi, Anna Borghi and Honghai Liu for fruitful discussions on the integrating context in cognitive systems. This work is partially funded by the Scientific and Technological Research Council of Turkey (TUB¨ ˙ITAK) through project no 111E287.",
year = "2014",
month = "12",
doi = "10.1109/DEVLRN.2014.6982982",
language = "English",
isbn = "9781479975419",
pages = "201--207",
booktitle = "2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Learning and using context on a humanoid robot using latent dirichlet allocation

AU - Celikkanat, Hande

AU - Orhan, Guner

AU - Pugeault, Nicolas

AU - Guerin, Frank

AU - Sahin, Erol

AU - Kalkan, Sinan

N1 - We would like to thank Angelo Cangelosi, Anna Borghi and Honghai Liu for fruitful discussions on the integrating context in cognitive systems. This work is partially funded by the Scientific and Technological Research Council of Turkey (TUB¨ ˙ITAK) through project no 111E287.

PY - 2014/12

Y1 - 2014/12

N2 - In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many relationships between objects and contexts, as well as between scenes and contexts.We use a concept web representation of the perceptions of the robot as a basis for context analysis. The detected contexts of the scene can be used for several cognitive problems. Our results demonstrate that the robot can use learned contexts to improve object recognition and planning.

AB - In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many relationships between objects and contexts, as well as between scenes and contexts.We use a concept web representation of the perceptions of the robot as a basis for context analysis. The detected contexts of the scene can be used for several cognitive problems. Our results demonstrate that the robot can use learned contexts to improve object recognition and planning.

UR - http://www.scopus.com/inward/record.url?scp=84920887650&partnerID=8YFLogxK

U2 - 10.1109/DEVLRN.2014.6982982

DO - 10.1109/DEVLRN.2014.6982982

M3 - Conference contribution

SN - 9781479975419

SP - 201

EP - 207

BT - 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -