paper-with-me

Papers

Toward a Harmonized Approach -- Requirement-based Structuring of a Safety Assurance Argumentation for Automated Vehicles

2025-05-06 · Marvin Loba, Nayel Fabian Salem, Marcus Nolte, Andreas Dotzler, Dieter Ludwig, Markus Maurer

Despite increasing testing operation on public roads, media reports on incidents show that safety issues remain to this day. One major cause factoring into this circumstance is high development uncertainty that manufacturers face when deploying these systems in an open context. In particular, one challenge is establishing a valid argument at design time that the vehicle will exhibit reasonable residual risk when operating in its intended operational design domain. Regulations, such as the European Implementing Regulation 2022/1426, require manufacturers to provide a safety assurance argumentation for SAE-Level-4 automated vehicles. While there is extensive literature on assurance cases for safety-critical systems, the domain of automated driving lacks explicit requirements regarding the creation of safety assurance argumentations. In this paper, we aim to narrow this gap by elaborating a requirement-based approach. We derive structural requirements for an argumentation from literature and supplement these with requirements derived from stakeholder concerns. We implement the requirements, yielding a proposal for an overall argumentation structure. The resulting "safety arguments" argue over four topic complexes: The developed product, the underlying process including its conformance/compliance to standards/laws, as well as the argumentations' context and soundness. Finally, we instantiate this structure with respect to domain-specific needs and principles.

📄 PDF Abstract BibTeX arXiv:2505.03709

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components

2022-02-10 · Michael Kläs, Lisa Jöckel, Rasmus Adler, Jan Reich

In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is…

A causal model of safety assurance for machine learning

2022-01-14 · Simon Burton

This paper proposes a framework based on a causal model of safety upon which effective safety assurance cases for ML-based applications can be built. In doing so, we build upon established principles of safety engineerin…

BIG-bench Machine Learning

AI Safety Training Can be Clinically Harmful

2026-04-25 · Suhas BN, Andrew M. Sherrill, Rosa I. Arriaga, Chris W. Wiese 외 arxiv

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological d…

On a Formal Model of Safe and Scalable Self-driving Cars

2017-08-21 · Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua

In recent years, car makers and tech companies have been racing towards self driving cars. It seems that the main parameter in this race is who will have the first car on the road. The goal of this paper is to add to the…

Autonomous DrivingSelf-Driving Cars

The missing link: Developing a safety case for perception components in automated driving

2021-08-30 · Rick Salay, Krzysztof Czarnecki, Hiroshi Kuwajima, Hirotoshi Yasuoka 외

Safety assurance is a central concern for the development and societal acceptance of automated driving (AD) systems. Perception is a key aspect of AD that relies heavily on Machine Learning (ML). Despite the known challe…