[Context and Motivation] The automotive industry is moving towards increased automation, where features such as automated driving systems typically include machine learning (ML), e.g. in the perception system. [Question/Problem] Ensuring safety for systems partly relying on ML is challenging. Different approaches and frameworks have been proposed, typically where the developer must define quantitative and/or qualitative acceptance criteria, and ensure the criteria are fulfilled using different methods to improve e.g., design, robustness and error detection. However, there is still a knowledge gap between quality methods and metrics employed in the ML domain and how such methods can contribute to satisfying the vehicle level safety requirements. [Principal Ideas/Results] In this paper, we argue the need for connecting available ML quality methods and metrics to the safety lifecycle and explicitly show their contribution to safety. In particular, we analyse Out-of-Distribution (OoD) detection, e.g., the frequency of novelty detection, and show its potential for multiple safety-related purposes. I.e., as (a) an acceptance criterion contributing to the decision if the software fulfills the safety requirements and hence is ready-for-release, (b) in operational design domain selection and expansion by including novelty samples into the training/development loop, and (c) as a run-time measure, e.g., if there is a sequence of novel samples, the vehicle should consider reaching a minimal risk condition. [Contribution] This paper describes the possibility to use OoD detection as a safety measure, and the potential contributions in different stages of the safety lifecycle.
@inproceedings{OoDSupportAD_refsq2023, title = {Out-of-Distribution Detection as Support for Autonomous Driving Safety Lifecycle}, author = {Henriksson, Jens and Ursing, Stig and Erdogan, Murat and Warg, Fredrik and Thorsén, Anders and Jaxing, Johan and Örsmark, Ola and Toftås, Mathias Örtenberg}, year = {2023}, month = {04}, abstract = {[Context and Motivation] The automotive industry is moving towards increased automation, where features such as automated driving systems typically include machine learning (ML), e.g. in the perception system. [Question/Problem] Ensuring safety for systems partly relying on ML is challenging. Different approaches and frameworks have been proposed, typically where the developer must define quantitative and/or qualitative acceptance criteria, and ensure the criteria are fulfilled using different methods to improve e.g., design, robustness and error detection. However, there is still a knowledge gap between quality methods and metrics employed in the ML domain and how such methods can contribute to satisfying the vehicle level safety requirements. [Principal Ideas/Results] In this paper, we argue the need for connecting available ML quality methods and metrics to the safety lifecycle and explicitly show their contribution to safety. In particular, we analyse Out-of-Distribution (OoD) detection, e.g., the frequency of novelty detection, and show its potential for multiple safety-related purposes. I.e., as (a) an acceptance criterion contributing to the decision if the software fulfills the safety requirements and hence is ready-for-release, (b) in operational design domain selection and expansion by including novelty samples into the training/development loop, and (c) as a run-time measure, e.g., if there is a sequence of novel samples, the vehicle should consider reaching a minimal risk condition. [Contribution] This paper describes the possibility to use OoD detection as a safety measure, and the potential contributions in different stages of the safety lifecycle.}, keywords = {Automotive safety, Out-of-Distribution detection, Machine learning, Automated driving systems, Safety requirements}, booktitle = {Requirements Engineering: Foundation for Software Quality (REFSQ 2023)}, doi = {10.1007/978-3-031-29786-1_16}, pages = {233--242}, isbn = {978-3-031-29786-1}, note = {Publication data: https://warg.org/fredrik/publ/} }