Fuzzy Interpretation of Operational Design Domains in Autonomous Driving

Salvi, Aniket; Weiss, Gereon; Trapp, Mario; Oboril, Fabian; Buerkle, Cornelius

doi:10.1109/iv51971.2022.9827061

Cited by 6 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…requiring a system's overall detection performance for objects located in closer proximity to be higher than for distant objects. This type of risk-based differentiation between performance targets on the level of the entire perception architecture would therefore already benefit from the use of multiple µODDs [21]. Within each of these µODDs, a performance target for each DL component is then determined based on the system architecture's redundancy (cf.…”

Section: A Risk and Performance Targetsmentioning

confidence: 99%

Towards the Quantitative Verification of Deep Learning for Safe Perception

Schleiss

Hagiwara

Kurzidem

et al. 2022

2022 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)

View full text Add to dashboard Cite

Deep learning (DL) is seen as an inevitable building block for perceiving the environment with sufficient detail and accuracy as required by automated driving functions. Despite this, its black-box nature and the therewith intertwined unpredictability still hinders its use in safety-critical systems. As such, this work addresses the problem of making this seemingly unpredictable nature measurable by providing a risk-based verification strategy, such as required by ISO 21448. In detail, a method is developed to break down acceptable risk into quantitative performance targets of individual DL-based components along the perception architecture. To verify these targets, the DL input space is split into areas according to the dimensions of a finegrained operational design domain (µODD). As it is not feasible to reach full test coverage, the strategy suggests to distribute test efforts across these areas according to the associated risk. Moreover, the testing approach provides answers with respect to how much test coverage and confidence in the test result is required and how these figures relate to safety integrity levels (SILs).

show abstract

Section: A Risk and Performance Targetsmentioning

confidence: 99%