On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics

Asuki Kouno, Jean Marc Montanier, Shigeru Takano, Nicolas Bredeche, Marc Schoenauer, Michèle Sebag, Einoshin Suzuki

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

1 Citation (Scopus)

Abstract

This paper aims at building autonomous controllers for swarm robots, specifically aimed at enforcing a given shape formation, here a column formation. The proposed approach features two main characteristics. Firstly, a state-of-the-art evolutionary setting is used to achieve the on-board optimization of the controller, avoiding any simulator-based approach. Secondly, as the cost of physical experiments might be prohibitively high for plain evolutionary approaches, a data mining approach is achieved on the top of evolution; rule discovery is used to discover the most promising regions in the controller search space. The merits of the approach are experimentally validated using a 5 robot formation, showing that the hybrid evolutionary learning process outperforms evolution alone in terms of swarm speed and shape quality.

Original languageEnglish
Title of host publicationProceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011
Pages220-227
Number of pages8
DOIs
Publication statusPublished - Nov 7 2011
Event2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011 - Lyon, France
Duration: Aug 22 2011Aug 27 2011

Publication series

NameProceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011
Volume2

Other

Other2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011
CountryFrance
CityLyon
Period8/22/118/27/11

Fingerprint

Evolutionary algorithms
Robotics
Controllers
Robots
Data mining
Simulators
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Kouno, A., Montanier, J. M., Takano, S., Bredeche, N., Schoenauer, M., Sebag, M., & Suzuki, E. (2011). On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics. In Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011 (pp. 220-227). [6040781] (Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011; Vol. 2). https://doi.org/10.1109/WI-IAT.2011.143

On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics. / Kouno, Asuki; Montanier, Jean Marc; Takano, Shigeru; Bredeche, Nicolas; Schoenauer, Marc; Sebag, Michèle; Suzuki, Einoshin.

Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. 2011. p. 220-227 6040781 (Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011; Vol. 2).

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

Kouno, A, Montanier, JM, Takano, S, Bredeche, N, Schoenauer, M, Sebag, M & Suzuki, E 2011, On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics. in Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011., 6040781, Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011, vol. 2, pp. 220-227, 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011, Lyon, France, 8/22/11. https://doi.org/10.1109/WI-IAT.2011.143
Kouno A, Montanier JM, Takano S, Bredeche N, Schoenauer M, Sebag M et al. On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics. In Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. 2011. p. 220-227. 6040781. (Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011). https://doi.org/10.1109/WI-IAT.2011.143
Kouno, Asuki ; Montanier, Jean Marc ; Takano, Shigeru ; Bredeche, Nicolas ; Schoenauer, Marc ; Sebag, Michèle ; Suzuki, Einoshin. / On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics. Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. 2011. pp. 220-227 (Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011).
@inproceedings{ab12b7ea6fed42a485c8465dba11a0d4,
title = "On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics",
abstract = "This paper aims at building autonomous controllers for swarm robots, specifically aimed at enforcing a given shape formation, here a column formation. The proposed approach features two main characteristics. Firstly, a state-of-the-art evolutionary setting is used to achieve the on-board optimization of the controller, avoiding any simulator-based approach. Secondly, as the cost of physical experiments might be prohibitively high for plain evolutionary approaches, a data mining approach is achieved on the top of evolution; rule discovery is used to discover the most promising regions in the controller search space. The merits of the approach are experimentally validated using a 5 robot formation, showing that the hybrid evolutionary learning process outperforms evolution alone in terms of swarm speed and shape quality.",
author = "Asuki Kouno and Montanier, {Jean Marc} and Shigeru Takano and Nicolas Bredeche and Marc Schoenauer and Mich{\`e}le Sebag and Einoshin Suzuki",
year = "2011",
month = "11",
day = "7",
doi = "10.1109/WI-IAT.2011.143",
language = "English",
isbn = "9780769545134",
series = "Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011",
pages = "220--227",
booktitle = "Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011",

}

TY - GEN

T1 - On-board evolutionary algorithm and off-line rule discovery for column formation in swarm robotics

AU - Kouno, Asuki

AU - Montanier, Jean Marc

AU - Takano, Shigeru

AU - Bredeche, Nicolas

AU - Schoenauer, Marc

AU - Sebag, Michèle

AU - Suzuki, Einoshin

PY - 2011/11/7

Y1 - 2011/11/7

N2 - This paper aims at building autonomous controllers for swarm robots, specifically aimed at enforcing a given shape formation, here a column formation. The proposed approach features two main characteristics. Firstly, a state-of-the-art evolutionary setting is used to achieve the on-board optimization of the controller, avoiding any simulator-based approach. Secondly, as the cost of physical experiments might be prohibitively high for plain evolutionary approaches, a data mining approach is achieved on the top of evolution; rule discovery is used to discover the most promising regions in the controller search space. The merits of the approach are experimentally validated using a 5 robot formation, showing that the hybrid evolutionary learning process outperforms evolution alone in terms of swarm speed and shape quality.

AB - This paper aims at building autonomous controllers for swarm robots, specifically aimed at enforcing a given shape formation, here a column formation. The proposed approach features two main characteristics. Firstly, a state-of-the-art evolutionary setting is used to achieve the on-board optimization of the controller, avoiding any simulator-based approach. Secondly, as the cost of physical experiments might be prohibitively high for plain evolutionary approaches, a data mining approach is achieved on the top of evolution; rule discovery is used to discover the most promising regions in the controller search space. The merits of the approach are experimentally validated using a 5 robot formation, showing that the hybrid evolutionary learning process outperforms evolution alone in terms of swarm speed and shape quality.

UR - http://www.scopus.com/inward/record.url?scp=80155195451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80155195451&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2011.143

DO - 10.1109/WI-IAT.2011.143

M3 - Conference contribution

AN - SCOPUS:80155195451

SN - 9780769545134

T3 - Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011

SP - 220

EP - 227

BT - Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011

ER -