Collective hyper-heuristics for self-assembling robot behaviours

Shuang Yu; Andy Song; Aldeida Aleti

doi:10.1007/978-3-319-97310-4_57

Collective hyper-heuristics for self-assembling robot behaviours

Shuang Yu, Andy Song, Aldeida Aleti

Department of Software Systems & Cybersecurity

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

1 Citation (Scopus)

Abstract

Swarm robots are highly desirable in dealing with complex tasks. However, manual coding of individual robot behaviours and robot collaboration is not trivial especially under unknown and dynamic environments. This study introduced a hyper-heuristic methodology for this challenge, so robots can learn suitable behaviours during the process. The hyper-heuristic method creates actions based on a set of low-level heuristics and improves these actions through autonomous heuristic adjustment. A collective negotiation and updating mechanism is proposed so the robot swarm performance can be improved. We evaluate this method on the problem of building surface cleaning. Experiments show the effectiveness of the hyper-heuristic method and the collective learning mechanism.

Original language	English
Title of host publication	PRICAI 2018: Trends in Artificial Intelligence
Subtitle of host publication	15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II
Editors	Xin Geng, Byeong-Ho Kang
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	499-507
Number of pages	9
ISBN (Electronic)	9783319973104
ISBN (Print)	9783319973098
DOIs	https://doi.org/10.1007/978-3-319-97310-4_57
Publication status	Published - 2018
Event	Pacific Rim International Conference on Artificial Intelligence 2018 - Nanjing, China Duration: 28 Aug 2018 → 31 Aug 2018 Conference number: 15th http://cse.seu.edu.cn/pricai18/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11013
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Pacific Rim International Conference on Artificial Intelligence 2018
Abbreviated title	PRICAI 2018
Country	China
City	Nanjing
Period	28/08/18 → 31/08/18
Internet address	http://cse.seu.edu.cn/pricai18/

Keywords

Collective behaviours
Hyper heuristics
Swarm robots

Access to Document

10.1007/978-3-319-97310-4_57

Link to publication in Scopus

Cite this

Yu, S., Song, A., & Aleti, A. (2018). Collective hyper-heuristics for self-assembling robot behaviours. In X. Geng, & B-H. Kang (Eds.), PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II (pp. 499-507). (Lecture Notes in Computer Science ; Vol. 11013 ). Springer. https://doi.org/10.1007/978-3-319-97310-4_57

Yu, Shuang ; Song, Andy ; Aleti, Aldeida. / Collective hyper-heuristics for self-assembling robot behaviours. PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II. editor / Xin Geng ; Byeong-Ho Kang. Cham Switzerland : Springer, 2018. pp. 499-507 (Lecture Notes in Computer Science ).

@inproceedings{bb06359ed0bc409a86b1e2f02f342144,

title = "Collective hyper-heuristics for self-assembling robot behaviours",

abstract = "Swarm robots are highly desirable in dealing with complex tasks. However, manual coding of individual robot behaviours and robot collaboration is not trivial especially under unknown and dynamic environments. This study introduced a hyper-heuristic methodology for this challenge, so robots can learn suitable behaviours during the process. The hyper-heuristic method creates actions based on a set of low-level heuristics and improves these actions through autonomous heuristic adjustment. A collective negotiation and updating mechanism is proposed so the robot swarm performance can be improved. We evaluate this method on the problem of building surface cleaning. Experiments show the effectiveness of the hyper-heuristic method and the collective learning mechanism.",

keywords = "Collective behaviours, Hyper heuristics, Swarm robots",

author = "Shuang Yu and Andy Song and Aldeida Aleti",

year = "2018",

doi = "10.1007/978-3-319-97310-4_57",

language = "English",

isbn = "9783319973098",

series = "Lecture Notes in Computer Science ",

publisher = "Springer",

pages = "499--507",

editor = "Geng, {Xin } and Kang, {Byeong-Ho }",

booktitle = "PRICAI 2018: Trends in Artificial Intelligence",

note = "Pacific Rim International Conference on Artificial Intelligence 2018, PRICAI 2018 ; Conference date: 28-08-2018 Through 31-08-2018",

url = "http://cse.seu.edu.cn/pricai18/",

}

Yu, S, Song, A & Aleti, A 2018, Collective hyper-heuristics for self-assembling robot behaviours. in X Geng & B-H Kang (eds), PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II. Lecture Notes in Computer Science , vol. 11013 , Springer, Cham Switzerland, pp. 499-507, Pacific Rim International Conference on Artificial Intelligence 2018, Nanjing, China, 28/08/18. https://doi.org/10.1007/978-3-319-97310-4_57

Collective hyper-heuristics for self-assembling robot behaviours. / Yu, Shuang; Song, Andy; Aleti, Aldeida.

PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II. ed. / Xin Geng; Byeong-Ho Kang. Cham Switzerland : Springer, 2018. p. 499-507 (Lecture Notes in Computer Science ; Vol. 11013 ).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Collective hyper-heuristics for self-assembling robot behaviours

AU - Yu, Shuang

AU - Song, Andy

AU - Aleti, Aldeida

N1 - Conference code: 15th

PY - 2018

Y1 - 2018

N2 - Swarm robots are highly desirable in dealing with complex tasks. However, manual coding of individual robot behaviours and robot collaboration is not trivial especially under unknown and dynamic environments. This study introduced a hyper-heuristic methodology for this challenge, so robots can learn suitable behaviours during the process. The hyper-heuristic method creates actions based on a set of low-level heuristics and improves these actions through autonomous heuristic adjustment. A collective negotiation and updating mechanism is proposed so the robot swarm performance can be improved. We evaluate this method on the problem of building surface cleaning. Experiments show the effectiveness of the hyper-heuristic method and the collective learning mechanism.

AB - Swarm robots are highly desirable in dealing with complex tasks. However, manual coding of individual robot behaviours and robot collaboration is not trivial especially under unknown and dynamic environments. This study introduced a hyper-heuristic methodology for this challenge, so robots can learn suitable behaviours during the process. The hyper-heuristic method creates actions based on a set of low-level heuristics and improves these actions through autonomous heuristic adjustment. A collective negotiation and updating mechanism is proposed so the robot swarm performance can be improved. We evaluate this method on the problem of building surface cleaning. Experiments show the effectiveness of the hyper-heuristic method and the collective learning mechanism.

KW - Collective behaviours

KW - Hyper heuristics

KW - Swarm robots

UR - http://www.scopus.com/inward/record.url?scp=85051994825&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-97310-4_57

DO - 10.1007/978-3-319-97310-4_57

M3 - Conference Paper

AN - SCOPUS:85051994825

SN - 9783319973098

T3 - Lecture Notes in Computer Science

SP - 499

EP - 507

BT - PRICAI 2018: Trends in Artificial Intelligence

A2 - Geng, Xin

A2 - Kang, Byeong-Ho

PB - Springer

CY - Cham Switzerland

T2 - Pacific Rim International Conference on Artificial Intelligence 2018

Y2 - 28 August 2018 through 31 August 2018

ER -

Yu S, Song A, Aleti A. Collective hyper-heuristics for self-assembling robot behaviours. In Geng X, Kang B-H, editors, PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence Nanjing, China, August 28–31, 2018 Proceedings, Part II. Cham Switzerland: Springer. 2018. p. 499-507. (Lecture Notes in Computer Science ). https://doi.org/10.1007/978-3-319-97310-4_57