Exogenous Fault Detection in Swarm Robotic Systems

Exogenous Fault Detection in Swarm Robotic Systems

Self Repairing Learning Rule for Spiking Astrocyte Neuron NetworksLiu, J., McDaid, L., Harkin, J., Wade, J., Karim, S., Johnson, A. P., Millard, A. G., Halliday, D. M., Tyrrell, A. M. Timmis, J. I. 27 Oct 2017 Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14 18, 2017, Proceeding, Part II. Liu, D., Xie, S., Li, Y., Zhao, D. El Alfy, E S. M. (eds.). Springer, (Lecture Notes in Computer Science; vol. 10634, 10635 10636, 10637, 10638, 10639)Research output: Chapter in Book/Report/Conference proceeding Conference contribution

Fault tolerant Learning in Spiking Astrocyte Neural Networks on FPGAsJohnson, A. P., Liu, J., Millard, A. G., Karim, S., Tyrrell, A. M., Harkin, J., Timmis, J. I., McDaid, L. Halliday, D. M. 15 Sep 2017 31st International Conference on VLSI Design (VLSID 2018) 17th International Conference on Embedded Systems (ES 2018). IEEEResearch output: Chapter in Book/Report/Conference proceeding Conference contribution

Homeostatic Fault Tolerance in Spiking Neural Networks utilizing Dynamic Partial Reconfiguration of FPGAsJohnson, A. P., Liu, J., Millard, A. G., Karim, S., Tyrrell, A. M., Harkin, J.,
Exogenous Fault Detection in Swarm Robotic Systems
Timmis, J. I., McDaid, L. Halliday, D. M. 15 Sep 2017 The International Conference on Field Programmable Technology (FPT 2017). IEEEResearch output: Chapter in Book/Report/Conference proceeding Conference contribution

Homeostatic Fault Tolerance in Spiking Neural Networks: A Dynamic Hardware PerspectiveJohnson, A. P., Liu, J., Millard, A. G., Karim, S., Tyrrell, A. M., Harkin, J., Timmis, J. I., McDaid, L. Halliday, D. M. 28 Jul 2017Article in Ieee transactions on circuits and systems i Regular papers

Assessing Self Repair on FPGAs with Biologically Realistic Astrocyte Neuron NetworksKarim, S., Harkin, J., McDaid, L., Gardiner, B., Liu, J., Halliday, D. M., Tyrrell, A. M., Timmis, J. I., Millard, A. G. Johnson, A. P. 24 Jul 2017 IEEE Xplore: IS VLSI. 6 p. ( VLSI (ISVLSI), IEEE Computer Society Annual Symposium on)Research output: Chapter in Book/Report/Conference proceeding Conference contribution

StandardExogenous Fault Detection in Swarm Robotic Systems : An Approach Based on Internal Models. / Millard, Alan Gregory.

White Rose University Consortium, 2016.

APAMillard, A. G. (2016). Exogenous Fault Detection in Swarm Robotic Systems: An Approach Based on Internal Models White Rose University Consortium

VancouverMillard AG. Exogenous Fault Detection in Swarm Robotic Systems: An Approach Based on Internal Models. White Rose University Consortium, 2016. 224 p. / Exogenous Fault Detection in Swarm Robotic Systems : An Approach Based on Internal Models. White Rose University Consortium, 2016. They are robust in the sense that the complete failure of individual robots will have little detrimental effect on a swarm’s overall collective behaviour. However, it has recently been shown that partially failed individuals may be harmful, and cause problems that cannot be solved by simply adding more robots to the swarm. Instead, an active approach to dealing with failed individuals is required for a swarm to continue operation in the face of partial failures. This thesis presents a novel method of exogenous fault detection that allows robots to detect the presence of faults in each other, via the comparison of expected and observed behaviour. Each robot predicts the expected behaviour of its neighbours by simulating them online in an internal replica of the real world. This expected behaviour is then compared against observations of their true behaviour, and any significant discrepancy is detected as a fault. They are robust in the sense that the complete failure of individual robots will have little detrimental effect on a swarm’s overall collective behaviour. However, it has recently been shown that partially failed individuals may be harmful, and cause problems that cannot be solved by simply adding more robots to the swarm. Instead, an active approach to dealing with failed individuals is required for a swarm to continue operation in the face of partial failures. This thesis presents a novel method of exogenous fault detection that allows robots to detect the presence of faults in each other, via the comparison of expected and observed behaviour. Each robot predicts the expected behaviour of its neighbours by simulating them online in an internal replica of the real world. This expected behaviour is then compared against observations of their true behaviour, and any significant discrepancy is detected as a fault. This work represents the first step towards a distributed fault detection, diagnosis, and recovery process that would afford robot swarms a high degree of fault tolerance, and facilitate long term autonomy.

AB Swarm robotic systems comprise many individual robots, and exhibit a degree of innate fault tolerance due to this built in redundancy. They are robust in the sense that the complete failure of individual robots will have little detrimental effect on a swarm’s overall collective behaviour. However, it has recently been shown that partially failed individuals may be harmful, and cause problems that cannot be solved by simply adding more robots to the swarm. Instead, an active approach to dealing with failed individuals is required for a swarm to continue operation in the face of partial failures. This thesis presents a novel method of exogenous fault detection that allows robots to detect the presence of faults in each other, via the comparison of expected and observed behaviour. Each robot predicts the expected behaviour of its neighbours by simulating them online in an internal replica of the real world. This expected behaviour is then compared against observations of their true behaviour, and any significant discrepancy is detected as a fault. This work represents the first step towards a distributed fault detection, diagnosis, and recovery process that would afford robot swarms a high degree of fault tolerance, and facilitate long term autonomy.
Exogenous Fault Detection in Swarm Robotic Systems