A review of testing object-based environment perception for safe automated driving

M Hoss, M Scholtes, L Eckstein - Automotive Innovation, 2022 - Springer
Safety assurance of automated driving systems must consider uncertain environment
perception. This paper reviews literature addressing how perception testing is realized as …

Understanding responsibility under uncertainty: A critical and sco** review of autonomous driving systems

F Rowe, M Jeanneret Medina… - Journal of …, 2024 - journals.sagepub.com
Autonomous driving systems (ADS) operate in an environment that is inherently complex. As
these systems may execute a task without the permission of a human agent, they raise major …

[PDF][PDF] Is uncertainty quantification in deep learning sufficient for out-of-distribution detection?

A Schwaiger, P Sinhamahapatra… - Aisafety …, 2020 - publica-rest.fraunhofer.de
Reliable information about the uncertainty of predictions from deep neural networks could
greatly facilitate their utilization in safety-critical applications. Current approaches for …

A comparison of uncertainty estimation approaches in deep learning components for autonomous vehicle applications

F Arnez, H Espinoza, A Radermacher… - arxiv preprint arxiv …, 2020 - arxiv.org
A key factor for ensuring safety in Autonomous Vehicles (AVs) is to avoid any abnormal
behaviors under undesirable and unpredicted circumstances. As AVs increasingly rely on …

Towards safety-aware pedestrian detection in autonomous systems

M Lyssenko, C Gladisch, C Heinzemann… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
In this paper, we present a framework to assess the quality of a pedestrian detector in an
autonomous driving scenario. To do this, we exploit performance metrics from the domain of …

Goal-aware RSS for complex scenarios via program logic

I Hasuo, C Eberhart, J Haydon, J Dubut… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
We introduce a goal-aware extension of responsibility-sensitive safety (RSS), a recent
methodology for rule-based safety guarantee for automated driving systems (ADS). Making …

Responsibility-sensitive safety: an introduction with an eye to logical foundations and formalization

I Hasuo - arxiv preprint arxiv:2206.03418, 2022 - arxiv.org
Responsibility-sensitive safety (RSS) is an approach to the safety of automated driving
systems (ADS). It aims to introduce mathematically formulated safety rules, compliance with …

RTA-IR: A runtime assurance framework for behavior planning based on imitation learning and responsibility-sensitive safety model

Y Peng, G Tan, H Si - Expert Systems with Applications, 2023 - Elsevier
Current research on artificial intelligence (AI) algorithms in safety–critical areas remains
extremely challenging due to their inability to be fully verified at design time. In this paper …

Architectural patterns for handling runtime uncertainty of data-driven models in safety-critical perception

J Groß, R Adler, M Kläs, J Reich, L Jöckel… - … Conference on Computer …, 2022 - Springer
Data-driven models (DDM) based on machine learning and other AI techniques play an
important role in the perception of increasingly autonomous systems. Due to the merely …

Robustifying controller specifications of cyber-physical systems against perceptual uncertainty

T Kobayashi, R Salay, I Hasuo, K Czarnecki… - NASA Formal Methods …, 2021 - Springer
Formal reasoning on the safety of controller systems interacting with plants is complex
because developers need to specify behavior while taking into account perceptual …