Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms

Suet Lee; Sabine Hauert

doi:10.1145/3597512.3597527

Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms

Suet Lee, Sabine Hauert

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

Abstract

As robot swarm applications move to the real-world, ensuring the safety of such systems will be critical for trust and adoption. Fault detection is an essential component in systems which require a level of safety. Previous work has identified metrics with high discriminatory power between faulty and normal states of a robot in the swarm. The method for identifying such metrics has been implemented in simulation. Here, we implement metric extraction in a real-world environment and evaluate whether the extracted metrics can overcome the “sim-to-real gap” - in other words how well it transfers from simulation to a real-world setting.

Original language	English
Title of host publication	TAS '23: Proceedings of the First International Symposium on Trustworthy Autonomous Systems
Publisher	Association for Computing Machinery (ACM)
Pages	1-3
Number of pages	3
ISBN (Electronic)	979-840070734-6
DOIs	https://doi.org/10.1145/3597512.3597527 https://doi.org/10.1145/3597512
Publication status	Published - 11 Jul 2023

Access to Document

Handle.net

Persistent link

UKRI Trustworthy Autonomous Systems Node In Functionality
Windsor, S. P. (Principal Investigator), Ives, J. C. S. (Co-Investigator), Downer, J. R. (Co-Investigator), Rossiter, J. M. (Co-Investigator), Eder, K. I. (Co-Investigator) & Hauert, S. (Co-Investigator)
1/11/20 → 30/04/24
Project: Research, Parent

Cite this

@inproceedings{7ae705abd55142e1832101c160c85803,

title = "Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms",

abstract = "As robot swarm applications move to the real-world, ensuring the safety of such systems will be critical for trust and adoption. Fault detection is an essential component in systems which require a level of safety. Previous work has identified metrics with high discriminatory power between faulty and normal states of a robot in the swarm. The method for identifying such metrics has been implemented in simulation. Here, we implement metric extraction in a real-world environment and evaluate whether the extracted metrics can overcome the “sim-to-real gap” - in other words how well it transfers from simulation to a real-world setting.",

author = "Suet Lee and Sabine Hauert",

year = "2023",

month = jul,

day = "11",

doi = "10.1145/3597512.3597527",

language = "English",

pages = "1--3",

booktitle = "TAS '23: Proceedings of the First International Symposium on Trustworthy Autonomous Systems",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

}

Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms. / Lee, Suet ; Hauert, Sabine.
TAS '23: Proceedings of the First International Symposium on Trustworthy Autonomous Systems. Association for Computing Machinery (ACM), 2023. p. 1-3 3597527.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms

AU - Lee, Suet

AU - Hauert, Sabine

PY - 2023/7/11

Y1 - 2023/7/11

N2 - As robot swarm applications move to the real-world, ensuring the safety of such systems will be critical for trust and adoption. Fault detection is an essential component in systems which require a level of safety. Previous work has identified metrics with high discriminatory power between faulty and normal states of a robot in the swarm. The method for identifying such metrics has been implemented in simulation. Here, we implement metric extraction in a real-world environment and evaluate whether the extracted metrics can overcome the “sim-to-real gap” - in other words how well it transfers from simulation to a real-world setting.

AB - As robot swarm applications move to the real-world, ensuring the safety of such systems will be critical for trust and adoption. Fault detection is an essential component in systems which require a level of safety. Previous work has identified metrics with high discriminatory power between faulty and normal states of a robot in the swarm. The method for identifying such metrics has been implemented in simulation. Here, we implement metric extraction in a real-world environment and evaluate whether the extracted metrics can overcome the “sim-to-real gap” - in other words how well it transfers from simulation to a real-world setting.

U2 - 10.1145/3597512.3597527

DO - 10.1145/3597512.3597527

M3 - Conference Contribution (Conference Proceeding)

SP - 1

EP - 3

BT - TAS '23: Proceedings of the First International Symposium on Trustworthy Autonomous Systems

PB - Association for Computing Machinery (ACM)

ER -

Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms

Abstract

Access to Document

Handle.net

Fingerprint

Projects

UKRI Trustworthy Autonomous Systems Node In Functionality

Cite this