Goal-aware team affiliation in collectives of autonomous robots

Lukas Esterle*

*Corresponding author for this work

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

Abstract

Collaboration in teams is essential in robot collectives. In order to achieve goals, individual robots would otherwise not be able to accomplish. In a such a distributed and highly dynamic system, a global coordination might not be possible. In this paper, we analyse static team affiliations, defined at deployment time, and compare its efficiency against dynamic team affiliations generated during runtime using random selection. Since operators might not be able to determine all dynamic aspects of the given environment at the time of deployment, we further propose a novel, goal-aware approach to affiliate each robot with a team. This approach brings together insights from biology, sociology, and psychology. In this novel approach, robots only operate on aggregated information from the network which is potentially changing during runtime. Finally, we also introduce an approach to select a team affiliation during runtime using machine learning techniques. Using 60,000 randomised scenarios, we analyse the efficiency and further discuss the different benefits and drawbacks of the proposed approaches.

Original languageEnglish
Title of host publicationProceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018
PublisherIEEE
Pages90-99
Number of pages10
Volume2018-September
ISBN (Electronic)9781538651728
ISBN (Print)978-1-5386-5173-5
DOIs
Publication statusPublished - 15 Jan 2019
Event12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018 - Trento, Italy
Duration: 3 Sep 20187 Sep 2018

Publication series

Name2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)
PublisherIEEE
ISSN (Print)1949-3673
ISSN (Electronic)1949-3681

Conference

Conference12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018
CountryItaly
CityTrento
Period3/09/187/09/18

Fingerprint

Robots
Learning systems
Dynamical systems

Keywords

  • collaboration
  • collectives
  • cooperation
  • division of labour
  • goal awareness
  • robotic systems
  • team affiliation

Cite this

Esterle, L. (2019). Goal-aware team affiliation in collectives of autonomous robots. In Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018 (Vol. 2018-September, pp. 90-99). [8614283] (2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)). IEEE. https://doi.org/10.1109/SASO.2018.00020
Esterle, Lukas. / Goal-aware team affiliation in collectives of autonomous robots. Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018. Vol. 2018-September IEEE, 2019. pp. 90-99 (2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)).
@inproceedings{9c1b6557e5514f928080e6698aefc704,
title = "Goal-aware team affiliation in collectives of autonomous robots",
abstract = "Collaboration in teams is essential in robot collectives. In order to achieve goals, individual robots would otherwise not be able to accomplish. In a such a distributed and highly dynamic system, a global coordination might not be possible. In this paper, we analyse static team affiliations, defined at deployment time, and compare its efficiency against dynamic team affiliations generated during runtime using random selection. Since operators might not be able to determine all dynamic aspects of the given environment at the time of deployment, we further propose a novel, goal-aware approach to affiliate each robot with a team. This approach brings together insights from biology, sociology, and psychology. In this novel approach, robots only operate on aggregated information from the network which is potentially changing during runtime. Finally, we also introduce an approach to select a team affiliation during runtime using machine learning techniques. Using 60,000 randomised scenarios, we analyse the efficiency and further discuss the different benefits and drawbacks of the proposed approaches.",
keywords = "collaboration, collectives, cooperation, division of labour, goal awareness, robotic systems, team affiliation",
author = "Lukas Esterle",
year = "2019",
month = "1",
day = "15",
doi = "10.1109/SASO.2018.00020",
language = "English",
isbn = "978-1-5386-5173-5",
volume = "2018-September",
series = "2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)",
publisher = "IEEE",
pages = "90--99",
booktitle = "Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018",
address = "United States",

}

Esterle, L 2019, Goal-aware team affiliation in collectives of autonomous robots. in Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018. vol. 2018-September, 8614283, 2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO), IEEE, pp. 90-99, 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018, Trento, Italy, 3/09/18. https://doi.org/10.1109/SASO.2018.00020

Goal-aware team affiliation in collectives of autonomous robots. / Esterle, Lukas.

Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018. Vol. 2018-September IEEE, 2019. p. 90-99 8614283 (2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)).

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

TY - GEN

T1 - Goal-aware team affiliation in collectives of autonomous robots

AU - Esterle, Lukas

PY - 2019/1/15

Y1 - 2019/1/15

N2 - Collaboration in teams is essential in robot collectives. In order to achieve goals, individual robots would otherwise not be able to accomplish. In a such a distributed and highly dynamic system, a global coordination might not be possible. In this paper, we analyse static team affiliations, defined at deployment time, and compare its efficiency against dynamic team affiliations generated during runtime using random selection. Since operators might not be able to determine all dynamic aspects of the given environment at the time of deployment, we further propose a novel, goal-aware approach to affiliate each robot with a team. This approach brings together insights from biology, sociology, and psychology. In this novel approach, robots only operate on aggregated information from the network which is potentially changing during runtime. Finally, we also introduce an approach to select a team affiliation during runtime using machine learning techniques. Using 60,000 randomised scenarios, we analyse the efficiency and further discuss the different benefits and drawbacks of the proposed approaches.

AB - Collaboration in teams is essential in robot collectives. In order to achieve goals, individual robots would otherwise not be able to accomplish. In a such a distributed and highly dynamic system, a global coordination might not be possible. In this paper, we analyse static team affiliations, defined at deployment time, and compare its efficiency against dynamic team affiliations generated during runtime using random selection. Since operators might not be able to determine all dynamic aspects of the given environment at the time of deployment, we further propose a novel, goal-aware approach to affiliate each robot with a team. This approach brings together insights from biology, sociology, and psychology. In this novel approach, robots only operate on aggregated information from the network which is potentially changing during runtime. Finally, we also introduce an approach to select a team affiliation during runtime using machine learning techniques. Using 60,000 randomised scenarios, we analyse the efficiency and further discuss the different benefits and drawbacks of the proposed approaches.

KW - collaboration

KW - collectives

KW - cooperation

KW - division of labour

KW - goal awareness

KW - robotic systems

KW - team affiliation

UR - http://www.scopus.com/inward/record.url?scp=85061902983&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/document/8614283

U2 - 10.1109/SASO.2018.00020

DO - 10.1109/SASO.2018.00020

M3 - Conference contribution

AN - SCOPUS:85061902983

SN - 978-1-5386-5173-5

VL - 2018-September

T3 - 2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)

SP - 90

EP - 99

BT - Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018

PB - IEEE

ER -

Esterle L. Goal-aware team affiliation in collectives of autonomous robots. In Proceedings - 12th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2018. Vol. 2018-September. IEEE. 2019. p. 90-99. 8614283. (2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)). https://doi.org/10.1109/SASO.2018.00020