Certification of Safe and Trusted Robotic Inspection of Assets

Fateme Dinmohammadi, Vincent Page, David Flynn, Valentin Robu, Michael Fisher, Charles Patchett, Michael Jump, Wenshuo Tang, Matt Webster

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

Abstract

In future inspections of offshore assets utilizing robots, robots will not only be expected to collate new data from their payload of instruments, but they will also be expected to interact with the infrastructure being inspected, undertake remedial tasks and engage with embedded monitoring systems of the asset. This increasing level of interaction and deployment frequency of robot inspections requires an understanding of how we can embed safe and trusted operational architectures within robots. Currently, robots can undertake constrained semi-autonomous inspections, using predetermined tasks (missions) with minimum supervision. However, the challenge is that the state of the world changes with time as does the condition of the robot. Therefore, robots must be able to undertake adaptive measures to support optimal outcomes during autonomous missions. In this paper, we propose an initial architecture to the safe verification and validation of health condition and certification of robotic and autonomous inspection systems for offshore assets. Our first contribution relates to the verification and validation architecture, which takes into account risks associated with asset inspection, safety protocols, evolving ambient changes, as well as the inherent state of health of the robot. The second part of our paper looks to how prognostic analytics can be used to support robot resilience in terms of sensor drift and accurate state of health estimates of critical sub-systems. Initial results demonstrate that methods such as relevance vector machines and Bayesian networks can be used to accurately mitigate risks to autonomy.
Original languageEnglish
Title of host publication2018 Prognostics and System Health Management Conference (PHM-Chongqing)
PublisherIEEE
Pages276-284
Number of pages9
ISBN (Electronic)9781538653807
DOIs
Publication statusPublished - 7 Jan 2019
Event2018 Prognostics and System Health Management Conference - Chongqing, China
Duration: 26 Oct 201828 Oct 2018

Publication series

NamePrognostics and System Health Management Conference (PHM-Chongqing)
PublisherIEEE
ISSN (Electronic)2166-5656

Conference

Conference2018 Prognostics and System Health Management Conference
Abbreviated titlePHM-Chongqing
CountryChina
CityChongqing
Period26/10/1828/10/18

Fingerprint

Robotics
Inspection
Robots
Health
Bayesian networks
Network protocols
Monitoring
Sensors

Keywords

  • Asset certification
  • Prognostic and health management (PHM)
  • Robotic inspection
  • Verification and validation

ASJC Scopus subject areas

  • Computer Science Applications
  • Safety, Risk, Reliability and Quality
  • Modelling and Simulation
  • Instrumentation

Cite this

Dinmohammadi, F., Page, V., Flynn, D., Robu, V., Fisher, M., Patchett, C., ... Webster, M. (2019). Certification of Safe and Trusted Robotic Inspection of Assets. In 2018 Prognostics and System Health Management Conference (PHM-Chongqing) (pp. 276-284). (Prognostics and System Health Management Conference (PHM-Chongqing)). IEEE. https://doi.org/10.1109/PHM-Chongqing.2018.00054
Dinmohammadi, Fateme ; Page, Vincent ; Flynn, David ; Robu, Valentin ; Fisher, Michael ; Patchett, Charles ; Jump, Michael ; Tang, Wenshuo ; Webster, Matt. / Certification of Safe and Trusted Robotic Inspection of Assets. 2018 Prognostics and System Health Management Conference (PHM-Chongqing). IEEE, 2019. pp. 276-284 (Prognostics and System Health Management Conference (PHM-Chongqing)).
@inproceedings{128f969b27e64ed38beab8286a0ea587,
title = "Certification of Safe and Trusted Robotic Inspection of Assets",
abstract = "In future inspections of offshore assets utilizing robots, robots will not only be expected to collate new data from their payload of instruments, but they will also be expected to interact with the infrastructure being inspected, undertake remedial tasks and engage with embedded monitoring systems of the asset. This increasing level of interaction and deployment frequency of robot inspections requires an understanding of how we can embed safe and trusted operational architectures within robots. Currently, robots can undertake constrained semi-autonomous inspections, using predetermined tasks (missions) with minimum supervision. However, the challenge is that the state of the world changes with time as does the condition of the robot. Therefore, robots must be able to undertake adaptive measures to support optimal outcomes during autonomous missions. In this paper, we propose an initial architecture to the safe verification and validation of health condition and certification of robotic and autonomous inspection systems for offshore assets. Our first contribution relates to the verification and validation architecture, which takes into account risks associated with asset inspection, safety protocols, evolving ambient changes, as well as the inherent state of health of the robot. The second part of our paper looks to how prognostic analytics can be used to support robot resilience in terms of sensor drift and accurate state of health estimates of critical sub-systems. Initial results demonstrate that methods such as relevance vector machines and Bayesian networks can be used to accurately mitigate risks to autonomy.",
keywords = "Asset certification, Prognostic and health management (PHM), Robotic inspection, Verification and validation",
author = "Fateme Dinmohammadi and Vincent Page and David Flynn and Valentin Robu and Michael Fisher and Charles Patchett and Michael Jump and Wenshuo Tang and Matt Webster",
year = "2019",
month = "1",
day = "7",
doi = "10.1109/PHM-Chongqing.2018.00054",
language = "English",
series = "Prognostics and System Health Management Conference (PHM-Chongqing)",
publisher = "IEEE",
pages = "276--284",
booktitle = "2018 Prognostics and System Health Management Conference (PHM-Chongqing)",
address = "United States",

}

Dinmohammadi, F, Page, V, Flynn, D, Robu, V, Fisher, M, Patchett, C, Jump, M, Tang, W & Webster, M 2019, Certification of Safe and Trusted Robotic Inspection of Assets. in 2018 Prognostics and System Health Management Conference (PHM-Chongqing). Prognostics and System Health Management Conference (PHM-Chongqing), IEEE, pp. 276-284, 2018 Prognostics and System Health Management Conference, Chongqing, China, 26/10/18. https://doi.org/10.1109/PHM-Chongqing.2018.00054

Certification of Safe and Trusted Robotic Inspection of Assets. / Dinmohammadi, Fateme; Page, Vincent; Flynn, David; Robu, Valentin; Fisher, Michael; Patchett, Charles; Jump, Michael; Tang, Wenshuo; Webster, Matt.

2018 Prognostics and System Health Management Conference (PHM-Chongqing). IEEE, 2019. p. 276-284 (Prognostics and System Health Management Conference (PHM-Chongqing)).

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

TY - GEN

T1 - Certification of Safe and Trusted Robotic Inspection of Assets

AU - Dinmohammadi, Fateme

AU - Page, Vincent

AU - Flynn, David

AU - Robu, Valentin

AU - Fisher, Michael

AU - Patchett, Charles

AU - Jump, Michael

AU - Tang, Wenshuo

AU - Webster, Matt

PY - 2019/1/7

Y1 - 2019/1/7

N2 - In future inspections of offshore assets utilizing robots, robots will not only be expected to collate new data from their payload of instruments, but they will also be expected to interact with the infrastructure being inspected, undertake remedial tasks and engage with embedded monitoring systems of the asset. This increasing level of interaction and deployment frequency of robot inspections requires an understanding of how we can embed safe and trusted operational architectures within robots. Currently, robots can undertake constrained semi-autonomous inspections, using predetermined tasks (missions) with minimum supervision. However, the challenge is that the state of the world changes with time as does the condition of the robot. Therefore, robots must be able to undertake adaptive measures to support optimal outcomes during autonomous missions. In this paper, we propose an initial architecture to the safe verification and validation of health condition and certification of robotic and autonomous inspection systems for offshore assets. Our first contribution relates to the verification and validation architecture, which takes into account risks associated with asset inspection, safety protocols, evolving ambient changes, as well as the inherent state of health of the robot. The second part of our paper looks to how prognostic analytics can be used to support robot resilience in terms of sensor drift and accurate state of health estimates of critical sub-systems. Initial results demonstrate that methods such as relevance vector machines and Bayesian networks can be used to accurately mitigate risks to autonomy.

AB - In future inspections of offshore assets utilizing robots, robots will not only be expected to collate new data from their payload of instruments, but they will also be expected to interact with the infrastructure being inspected, undertake remedial tasks and engage with embedded monitoring systems of the asset. This increasing level of interaction and deployment frequency of robot inspections requires an understanding of how we can embed safe and trusted operational architectures within robots. Currently, robots can undertake constrained semi-autonomous inspections, using predetermined tasks (missions) with minimum supervision. However, the challenge is that the state of the world changes with time as does the condition of the robot. Therefore, robots must be able to undertake adaptive measures to support optimal outcomes during autonomous missions. In this paper, we propose an initial architecture to the safe verification and validation of health condition and certification of robotic and autonomous inspection systems for offshore assets. Our first contribution relates to the verification and validation architecture, which takes into account risks associated with asset inspection, safety protocols, evolving ambient changes, as well as the inherent state of health of the robot. The second part of our paper looks to how prognostic analytics can be used to support robot resilience in terms of sensor drift and accurate state of health estimates of critical sub-systems. Initial results demonstrate that methods such as relevance vector machines and Bayesian networks can be used to accurately mitigate risks to autonomy.

KW - Asset certification

KW - Prognostic and health management (PHM)

KW - Robotic inspection

KW - Verification and validation

UR - http://www.scopus.com/inward/record.url?scp=85061767872&partnerID=8YFLogxK

U2 - 10.1109/PHM-Chongqing.2018.00054

DO - 10.1109/PHM-Chongqing.2018.00054

M3 - Conference contribution

T3 - Prognostics and System Health Management Conference (PHM-Chongqing)

SP - 276

EP - 284

BT - 2018 Prognostics and System Health Management Conference (PHM-Chongqing)

PB - IEEE

ER -

Dinmohammadi F, Page V, Flynn D, Robu V, Fisher M, Patchett C et al. Certification of Safe and Trusted Robotic Inspection of Assets. In 2018 Prognostics and System Health Management Conference (PHM-Chongqing). IEEE. 2019. p. 276-284. (Prognostics and System Health Management Conference (PHM-Chongqing)). https://doi.org/10.1109/PHM-Chongqing.2018.00054