Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification

Felix Batsch; Alireza Daneshkhah; Madeline Cheah; Stratis Kanarachos; Anthony  Baxendale

doi:10.1109/ITSC.2019.8917119

Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification

Felix Batsch, Alireza Daneshkhah, Madeline Cheah, Stratis Kanarachos, Anthony Baxendale

HORIBA MIRA Ltd.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

28 Citations (Scopus)

88 Downloads (Pure)

Abstract

Safety is an essential aspect in the facilitation of automated vehicle deployment. Current testing practices are not enough, and going beyond them leads to infeasible testing requirements, such as needing to drive billions of kilometres on public roads. Automated vehicles are exposed to an indefinite number of scenarios. Handling of the most challenging scenarios should be tested, which leads to the question of how such corner cases can be determined. We propose an approach to identify the performance boundary, where these corner cases are located, using Gaussian Process Classification. We also demonstrate the classification on an exemplary traffic jam approach scenario, showing that it is feasible and would lead to more efficient testing practices.

Original language	English
Title of host publication	2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019
Publisher	IEEE
Pages	419-424
Number of pages	6
ISBN (Electronic)	978-1-5386-7024-8
ISBN (Print)	978-1-5386-7025-5
DOIs	https://doi.org/10.1109/ITSC.2019.8917119
Publication status	Published - 2019
Event	22nd IEEE International Conference on Intelligent Transportation Systems - Auckland, New Zealand Duration: 27 Oct 2019 → 30 Oct 2019

Conference

Conference	22nd IEEE International Conference on Intelligent Transportation Systems
Abbreviated title	ITSC 2019
Country/Territory	New Zealand
City	Auckland
Period	27/10/19 → 30/10/19

ASJC Scopus subject areas

Artificial Intelligence
Management Science and Operations Research
Instrumentation
Transportation

Access to Document

10.1109/ITSC.2019.8917119

Post-PrintAccepted author manuscript, 0.98 MBLicence: Unspecified

Cite this

Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification. / Batsch, Felix; Daneshkhah, Alireza; Cheah, Madeline et al.
2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019. IEEE, 2019. p. 419-424 8917119.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Batsch, F, Daneshkhah, A, Cheah, M, Kanarachos, S & Baxendale, A 2019, Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification. in 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019., 8917119, IEEE, pp. 419-424, 22nd IEEE International Conference on Intelligent Transportation Systems, Auckland, New Zealand, 27/10/19. https://doi.org/10.1109/ITSC.2019.8917119

@inproceedings{9b49491ac6524ea28afbdbdb98fa3520,

title = "Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification",

abstract = "Safety is an essential aspect in the facilitation of automated vehicle deployment. Current testing practices are not enough, and going beyond them leads to infeasible testing requirements, such as needing to drive billions of kilometres on public roads. Automated vehicles are exposed to an indefinite number of scenarios. Handling of the most challenging scenarios should be tested, which leads to the question of how such corner cases can be determined. We propose an approach to identify the performance boundary, where these corner cases are located, using Gaussian Process Classification. We also demonstrate the classification on an exemplary traffic jam approach scenario, showing that it is feasible and would lead to more efficient testing practices.",

author = "Felix Batsch and Alireza Daneshkhah and Madeline Cheah and Stratis Kanarachos and Anthony Baxendale",

year = "2019",

doi = "10.1109/ITSC.2019.8917119",

language = "English",

isbn = "978-1-5386-7025-5",

pages = "419--424",

booktitle = "2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019",

publisher = "IEEE",

address = "United States",

note = "22nd IEEE International Conference on Intelligent Transportation Systems, ITSC 2019 ; Conference date: 27-10-2019 Through 30-10-2019",

}

TY - GEN

T1 - Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification

AU - Batsch, Felix

AU - Daneshkhah, Alireza

AU - Cheah, Madeline

AU - Kanarachos, Stratis

AU - Baxendale, Anthony

PY - 2019

Y1 - 2019

N2 - Safety is an essential aspect in the facilitation of automated vehicle deployment. Current testing practices are not enough, and going beyond them leads to infeasible testing requirements, such as needing to drive billions of kilometres on public roads. Automated vehicles are exposed to an indefinite number of scenarios. Handling of the most challenging scenarios should be tested, which leads to the question of how such corner cases can be determined. We propose an approach to identify the performance boundary, where these corner cases are located, using Gaussian Process Classification. We also demonstrate the classification on an exemplary traffic jam approach scenario, showing that it is feasible and would lead to more efficient testing practices.

AB - Safety is an essential aspect in the facilitation of automated vehicle deployment. Current testing practices are not enough, and going beyond them leads to infeasible testing requirements, such as needing to drive billions of kilometres on public roads. Automated vehicles are exposed to an indefinite number of scenarios. Handling of the most challenging scenarios should be tested, which leads to the question of how such corner cases can be determined. We propose an approach to identify the performance boundary, where these corner cases are located, using Gaussian Process Classification. We also demonstrate the classification on an exemplary traffic jam approach scenario, showing that it is feasible and would lead to more efficient testing practices.

UR - https://ieeexplore.ieee.org/document/8917119

UR - http://www.scopus.com/inward/record.url?scp=85076817788&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2019.8917119

DO - 10.1109/ITSC.2019.8917119

M3 - Conference proceeding

SN - 978-1-5386-7025-5

SP - 419

EP - 424

BT - 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019

PB - IEEE

T2 - 22nd IEEE International Conference on Intelligent Transportation Systems

Y2 - 27 October 2019 through 30 October 2019

ER -

Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this