This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Putting Safety of Intended Functionality SOTIF into Practice
Technical Paper
2021-01-0196
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Event:
SAE WCX Digital Summit
Language:
English
Abstract
The increase of autonomy demand in the automotive industry made the usage of AI models inevitable. However, such models introduce a variety of threats to automobile safety and security. ISO/PAS 21448 SOTIF is a safety standard that is designed to deal with risks due to non-electrical and non-electronic failures. In this paper we put SOTIF into practice. In our work we introduce a conceivable safety critical scenario that targets the lane keep assist function. We use the suggested modelling techniques in the SOTIF standard to analyze the scenario and extract the trigger event. In result, we propose a contextual based predictive ML model to monitor the intervention between the driver and lane keep assist system. Our approach followed the SOTIF verification and validation guidelines. Empirically, we use a real safety critical scenario dataset as well as an augmented dataset. Our results show a high precision/recall values that exceed 90% by an increase of more than 150% in f1 score compared to non contextual models. It also showed that there is a trade-off relation between the precision/recall values and the sensitivity of models to its inputs.
Recommended Content
| Technical Paper | Leveraging Systems Theoretic Process Analysis (STPA) for Efficient ISO 26262 Compliance |
| Technical Paper | Integration of Multiple Active Safety Systems using STPA |
| Ground Vehicle Standard | Adaptive Cruise Control (ACC) Operating Characteristics and User Interface |
Authors
Citation
Abdulazim, A., Elbahaey, M., and Mohamed, A., "Putting Safety of Intended Functionality SOTIF into Practice," SAE Technical Paper 2021-01-0196, 2021, https://doi.org/10.4271/2021-01-0196.Data Sets - Support Documents
| Title | Description | Download |
|---|---|---|
| Unnamed Dataset 1 | ||
| Unnamed Dataset 2 |
Also In
References
- Kirovskii , O.M. , and Gorelov , V.A. Driver Assistance Systems: Analysis, Tests and the Safety Case. ISO 26262 and ISO PAS 21448 IOP Conference Series: Materials Science and Engineering 534 012019 Jun 2019
- Gharib , M. , Lollini , P. , Botta , M. , Amparore , E. , Donatelli , S. , and Bondavalli , A. On the Safety of Automotive Systems Incorporating Machine Learning Based Components: A Position Paper 2018 48thAnnual IEEE/IFIP International Conference on Dependable Systemsand Networks Workshops (DSN-W) 271 274 2018
- Varshney , K.R. Engineering Safety in Machine Learning 2016 Information Theory and Applications Workshop (ITA) 1 5 2016
- Varshney , K.R. and Alemzadeh , H. On the Safety of Machine Learning: Cyber-physical Systems, Decision Sciences, and Data Products 2016
- Liu , F. , and Yang , M. Verification and Validation of Artificial Neural Network Models Zhang , S. , Jarvis , R. AI 2005: Advances in Artificial Intelligence Berlin, Heidelberg Springer Berlin Heidelberg 2005 1041 1046
- Koopman , P. , and Wagner , M. Challenges in Autonomous Vehicle Testing and Validation SAE Int. J. Trans. Safety 4 15 24 April 2016
- Schumann , J. , Gupta , P. , and Liu , Y. Application of Neural Networksin High Assurance Systems: A Survey Berlin, Heidelberg Springer Berlin Heidelberg 2010 1 19
- SAE, T 2013
- Iso/pas 21448: 2019 2020
- Schnellbach , A. , and Griessnig , G. Development of the ISO 21448 Walker , A. , O’Connor , R.V. , and Messnarz , R. Systems, Software and Services Process Improvement Cham Springer International Publishing 2019 585 593
- Schwalb , E. Analysis of Safety of the Intended Use (sotif)
- Burton , S. , Gauerhof , L. , and Heinzemann , C. Making the Case for Safety of Machine Learning in Highly Automated Driving Tonetta , S. , Schoitsch , E. , and Bitsch , F. Computer Safety, Reliability, and Security Cham Springer International Publishing 2017 5 16
- Bodenhausen , U. Architecture and Independence Controller for Deep Learning in Safety Critical Applications Bargende , M. , Reuss , H.-C. , Wagner , A. , and Wiedemann , J. 19. Internationales Stuttgarter Symposium Wiesbaden Springer Fachmedien Wiesbaden 2019 1131 1142
- Guo , M. , Shang , S. , Haifeng , C. , Zhang , K. et al. Control Model of Automated Driving Systems Based on Sotif Evaluation SAE Technical Paper 2020-01-1214 2020 https://doi.org/10.4271/2020-01-1214
- Burton , S. , Gauerhof , L. , Sethy , B.B. , Habli , I. , and Hawkins , R. Confidence Arguments for Evidence of Performance in Machine Learning for Highly Automated Driving Functions Romanovsky , A. , Troubitsyna , E. , Gashi , I. , Schoitsch , E. , and Bitsch , F. Computer Safety, Reliability, and Security Cham Springer International Publishing 2019 365 377
- Cho , K.-T. and Shin , K.G. Fingerprinting Electronic Control Units for Vehicle Intrusion Detection 25th USENIX Security Symposium (USENIX Security 16) Austin, TX 911 927 Aug. 2016
- Cho , K. , and Shin , K.G. Viden: Attacker Identification on In-Vehicle Networks CoRR abs/1708.08414 2017
- Hawkins , S. , He , H. , Williams , G. , and Baxter , R. Outlier Detection Using Replicator Neural Networks 2454 113 123 2002