Yes / This article proposes an approach named SafeML II, which applies empirical cumulative distribution function-based statistical distance measures in a designed human-in-the loop procedure to ensure the safety of machine learning-based classifiers in autonomous vehicle software.
The application of artificial intelligence (AI) and
data-driven decision-making systems in autonomous vehicles is
growing rapidly. As autonomous vehicles operate in dynamic
environments, the risk that they can face an unknown observation
is relatively high due to insufficient training data, distributional
shift, or cyber-security attack. Thus, AI-based algorithms should
make dependable decisions to improve their interpretation of the
environment, lower the risk of autonomous driving, and avoid
catastrophic accidents. This paper proposes an approach named
SafeML II, which applies empirical cumulative distribution
function (ECDF)-based statistical distance measures in a designed
human-in-the-loop procedure to ensure the safety of machine
learning-based classifiers in autonomous vehicle software. The
approach is model-agnostic and it can cover various machine
learning and deep learning classifiers. The German Traffic
Sign Recognition Benchmark (GTSRB) is used to illustrate the
capabilities of the proposed approach. / This work was supported by the Secure and Safe MultiRobot Systems (SESAME) H2020 Project under Grant Agreement 101017258.
| Identifer | oai:union.ndltd.org:BRADFORD/oai:bradscholars.brad.ac.uk:10454/18591 |
| Date | 10 August 2021 |
| Creators | Aslansefat, K., Kabir, Sohag, Abdullatif, Amr R.A., Vasudevan, Vinod, Papadopoulos, Y. |
| Publisher | IEEE |
| Source Sets | Bradford Scholars |
| Language | English |
| Detected Language | English |
| Type | Article, Accepted manuscript |
| Rights | © 2021 IEEE. Reproduced in accordance with the publisher's self-archiving policy. |
Page generated in 0.0021 seconds