Adaptive data-driven error detection in swarm robotic systems with statistical classifiers

Research output: Contribution to journalArticle

Standard

Adaptive data-driven error detection in swarm robotic systems with statistical classifiers. / Lau, Hui; Bate, Iain John; Cairns, Paul Antony; Timmis, Jon.

In: Robotics and Autonomous Systems, Vol. 59, No. 12, 01.12.2011, p. 1021-1035.

Research output: Contribution to journalArticle

Harvard

Lau, H, Bate, IJ, Cairns, PA & Timmis, J 2011, 'Adaptive data-driven error detection in swarm robotic systems with statistical classifiers', Robotics and Autonomous Systems, vol. 59, no. 12, pp. 1021-1035. https://doi.org/10.1016/j.robot.2011.08.008

APA

Lau, H., Bate, I. J., Cairns, P. A., & Timmis, J. (2011). Adaptive data-driven error detection in swarm robotic systems with statistical classifiers. Robotics and Autonomous Systems, 59(12), 1021-1035. https://doi.org/10.1016/j.robot.2011.08.008

Vancouver

Lau H, Bate IJ, Cairns PA, Timmis J. Adaptive data-driven error detection in swarm robotic systems with statistical classifiers. Robotics and Autonomous Systems. 2011 Dec 1;59(12):1021-1035. https://doi.org/10.1016/j.robot.2011.08.008

Author

Lau, Hui ; Bate, Iain John ; Cairns, Paul Antony ; Timmis, Jon. / Adaptive data-driven error detection in swarm robotic systems with statistical classifiers. In: Robotics and Autonomous Systems. 2011 ; Vol. 59, No. 12. pp. 1021-1035.

Bibtex - Download

@article{5083849ed989443c98c7d03f1a9b94a1,
title = "Adaptive data-driven error detection in swarm robotic systems with statistical classifiers",
abstract = "Swarm robotics is an example of a complex system with interactions among distributed autonomous robots as well with the environment. Within the swarm there is no centralised control, behaviour emerges from interactions between agents within the swarm. Agents within the swarm exhibit time varying behaviour in dynamic environments, and are subject to a variety of possible anomalies. The focus within our work is on specific faults in individual robots that can affect the global performance of the robotic swarm. We argue that classical approaches for achieving tolerance through implicit redundancy is insufficient in some cases and additional measures should be explored. Our contribution is to demonstrate that tolerance through explicit detection with statistical techniques works well and is suitable due to its lightweight computation.",
author = "Hui Lau and Bate, {Iain John} and Cairns, {Paul Antony} and Jon Timmis",
year = "2011",
month = "12",
day = "1",
doi = "10.1016/j.robot.2011.08.008",
language = "English",
volume = "59",
pages = "1021--1035",
journal = "Robotics and Autonomous Systems",
issn = "0921-8890",
publisher = "Elsevier",
number = "12",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Adaptive data-driven error detection in swarm robotic systems with statistical classifiers

AU - Lau, Hui

AU - Bate, Iain John

AU - Cairns, Paul Antony

AU - Timmis, Jon

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Swarm robotics is an example of a complex system with interactions among distributed autonomous robots as well with the environment. Within the swarm there is no centralised control, behaviour emerges from interactions between agents within the swarm. Agents within the swarm exhibit time varying behaviour in dynamic environments, and are subject to a variety of possible anomalies. The focus within our work is on specific faults in individual robots that can affect the global performance of the robotic swarm. We argue that classical approaches for achieving tolerance through implicit redundancy is insufficient in some cases and additional measures should be explored. Our contribution is to demonstrate that tolerance through explicit detection with statistical techniques works well and is suitable due to its lightweight computation.

AB - Swarm robotics is an example of a complex system with interactions among distributed autonomous robots as well with the environment. Within the swarm there is no centralised control, behaviour emerges from interactions between agents within the swarm. Agents within the swarm exhibit time varying behaviour in dynamic environments, and are subject to a variety of possible anomalies. The focus within our work is on specific faults in individual robots that can affect the global performance of the robotic swarm. We argue that classical approaches for achieving tolerance through implicit redundancy is insufficient in some cases and additional measures should be explored. Our contribution is to demonstrate that tolerance through explicit detection with statistical techniques works well and is suitable due to its lightweight computation.

U2 - 10.1016/j.robot.2011.08.008

DO - 10.1016/j.robot.2011.08.008

M3 - Article

VL - 59

SP - 1021

EP - 1035

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

IS - 12

ER -