Collective self-detection scheme for adaptive error detection in a foraging swarm of robots

Authors:
HuiKeng Lau;Jon Timmis;Iain Bate
Affiliations:
Department of Computer Science, University of York Heslington, UK and School of Engineering and IT, Universiti Malaysia Sabah, Kota Kinabalu, Sabah, Malaysia;Department of Computer Science, University of York Heslington, UK and Department of Electronics;Department of Computer Science, University of York Heslington, UK
Venue:
ICARIS'11 Proceedings of the 10th international conference on Artificial immune systems
Year:
2011

Citing 5
Cited 1

Automatic Synthesis of Fault Detection Modules for Mobile Robots

AHS '07 Proceedings of the Second NASA/ESA Conference on Adaptive Hardware and Systems
T Cell Receptor Signalling Inspired Kernel Density Estimation and Anomaly Detection

ICARIS '09 Proceedings of the 8th International Conference on Artificial Immune Systems
A modified dendritic cell algorithm for on-line error detection in robotic systems

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Exogenous fault detection in a collective robotic task

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Swarm robotics: from sources of inspiration to domains of application

SAB'04 Proceedings of the 2004 international conference on Swarm Robotics

Immune-Inspired self healing in wireless sensor networks

ICARIS'12 Proceedings of the 11th international conference on Artificial Immune Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a collective detection scheme using receptor density algorithm to self-detect certain types of failure in swarm robotic systems. Key to any fault-tolerant system, is its ability to be robust to failure and have appropriate mechanisms to cope with a variety of such failures. In this work we present an error detection scheme based on T-cell signalling in which robots in a swarm collaborate by exchanging information with respect to performance on a given task, and self-detect errors within an individual. While this study is focused on deployment in a swarm robotic context, it is possible that our approach could possibly be generalized to a wider variety of multi-agent systems.