Autonomous learning of robust visual object detection and identification on a humanoid

J. Leitner; P. Chandrashekhariah; S. Harding; M. Frank; G. Spina; A. Förster; J. Triesch; J. Schmidhuber

doi:10.1109/DevLrn.2012.6400826

Autonomous learning of robust visual object detection and identification on a humanoid

J. Leitner, P. Chandrashekhariah, S. Harding, M. Frank, G. Spina, A. Förster, J. Triesch, J. Schmidhuber

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

5 Citations (Scopus)

Abstract

In this work we introduce a technique for a humanoid robot to autonomously learn the representations of objects within its visual environment. Our approach involves an attention mechanism in association with feature based segmentation that explores the environment and provides object samples for training. These samples are learned for further object identification using Cartesian Genetic Programming (CGP). The learned identification is able to provide robust and fast segmentation of the objects, without using features. We showcase our system and its performance on the iCub humanoid robot.

Original language	English
Title of host publication	Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego
Place of Publication	San Diego
DOIs	https://doi.org/10.1109/DevLrn.2012.6400826
Publication status	Published - 2012
Event	conference; IEEE Conference on Development and Learning, and Epigenetic Robotics; 2012-11-07; 2012-11-09 - Duration: 7 Nov 2012 → 9 Nov 2012

Conference

Conference	conference; IEEE Conference on Development and Learning, and Epigenetic Robotics; 2012-11-07; 2012-11-09
Period	7/11/12 → 9/11/12
Other	IEEE Conference on Development and Learning, and Epigenetic Robotics

Access to Document

10.1109/DevLrn.2012.6400826

Cite this

Leitner, J., Chandrashekhariah, P., Harding, S., Frank, M., Spina, G., Förster, A., Triesch, J., & Schmidhuber, J. (2012). Autonomous learning of robust visual object detection and identification on a humanoid. In Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego https://doi.org/10.1109/DevLrn.2012.6400826

@inproceedings{ab6b9363e8e64b3a8a9c8761477f97c2,

title = "Autonomous learning of robust visual object detection and identification on a humanoid",

abstract = "In this work we introduce a technique for a humanoid robot to autonomously learn the representations of objects within its visual environment. Our approach involves an attention mechanism in association with feature based segmentation that explores the environment and provides object samples for training. These samples are learned for further object identification using Cartesian Genetic Programming (CGP). The learned identification is able to provide robust and fast segmentation of the objects, without using features. We showcase our system and its performance on the iCub humanoid robot.",

author = "J. Leitner and P. Chandrashekhariah and S. Harding and M. Frank and G. Spina and A. F{\"o}rster and J. Triesch and J. Schmidhuber",

year = "2012",

doi = "10.1109/DevLrn.2012.6400826",

language = "English",

isbn = "978-1-4673-4964-2",

booktitle = "Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego",

note = "conference; IEEE Conference on Development and Learning, and Epigenetic Robotics; 2012-11-07; 2012-11-09 ; Conference date: 07-11-2012 Through 09-11-2012",

}

Leitner, J, Chandrashekhariah, P, Harding, S, Frank, M, Spina, G, Förster, A, Triesch, J & Schmidhuber, J 2012, Autonomous learning of robust visual object detection and identification on a humanoid. in Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego. San Diego, conference; IEEE Conference on Development and Learning, and Epigenetic Robotics; 2012-11-07; 2012-11-09, 7/11/12. https://doi.org/10.1109/DevLrn.2012.6400826

Autonomous learning of robust visual object detection and identification on a humanoid. / Leitner, J.; Chandrashekhariah, P.; Harding, S. et al.
Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego. San Diego, 2012.

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

TY - GEN

T1 - Autonomous learning of robust visual object detection and identification on a humanoid

AU - Leitner, J.

AU - Chandrashekhariah, P.

AU - Harding, S.

AU - Frank, M.

AU - Spina, G.

AU - Förster, A.

AU - Triesch, J.

AU - Schmidhuber, J.

PY - 2012

Y1 - 2012

N2 - In this work we introduce a technique for a humanoid robot to autonomously learn the representations of objects within its visual environment. Our approach involves an attention mechanism in association with feature based segmentation that explores the environment and provides object samples for training. These samples are learned for further object identification using Cartesian Genetic Programming (CGP). The learned identification is able to provide robust and fast segmentation of the objects, without using features. We showcase our system and its performance on the iCub humanoid robot.

AB - In this work we introduce a technique for a humanoid robot to autonomously learn the representations of objects within its visual environment. Our approach involves an attention mechanism in association with feature based segmentation that explores the environment and provides object samples for training. These samples are learned for further object identification using Cartesian Genetic Programming (CGP). The learned identification is able to provide robust and fast segmentation of the objects, without using features. We showcase our system and its performance on the iCub humanoid robot.

U2 - 10.1109/DevLrn.2012.6400826

DO - 10.1109/DevLrn.2012.6400826

M3 - Conference contribution

SN - 978-1-4673-4964-2

BT - Proceedings of the IEEE Conference on Development and Learning, and Epigenetic Robotics (ICDL), 7-9 November 2012, San Diego

CY - San Diego

T2 - conference; IEEE Conference on Development and Learning, and Epigenetic Robotics; 2012-11-07; 2012-11-09

Y2 - 7 November 2012 through 9 November 2012

ER -

Autonomous learning of robust visual object detection and identification on a humanoid

Abstract

Conference

Access to Document

Fingerprint

Cite this