A Systematic Literature Review on Safety of the Intended Functionality for Automated Driving Systems
DOI: 10.4271/2025-01-5030
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper presents a systematic literature review (SLR) addressing the Safety of the Intended Functionality (SOTIF) for Automated Driving Systems (ADS), guided by ISO 21448. The research is motivated by the increasing complexity of ADS, which rely on perception sensors and machine learning algorithms that may exhibit functional insufficiencies or performance limitations rather than hardware malfunctions. Unlike Functional Safety, which addresses random hardware failures, SOTIF focuses on hazards arising from system design limitations, sensor performance issues, and foreseeable misuse. The study aims to synthesize existing knowledge, identify research gaps, and propose future directions to ensure ADS operate safely within their intended operational design domains. The authors conducted the SLR following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search strategy queried databases including ACM Digital Library, IEEE Xplore, SAE Mobilus, Dimensions, arXiv, and Springer using keywords related to SOTIF, ISO 21448, and ADS. The initial search yielded 1,014 records. After removing duplicates and applying exclusion criteria—such as publication date (post-2018), language, and relevance to SOTIF—550 records remained. These underwent screening and quality assessment based on peer-review status, practical or research value, and adequate coverage of SOTIF context. Following the exclusion of extended versions to avoid redundancy, 51 unique research papers published between 2018 and 2023 were included in the final analysis. The review synthesizes findings from the 51 selected papers, categorizing them into thematic groups and analyzing acknowledged limitations. The study addresses three primary research questions: factors associated with successful SOTIF implementation, safety challenges in ensuring SOTIF for ADS, and identified research gaps. Key findings highlight the necessity of a holistic approach involving risk assessment, scenario-based testing, and simulation to verify system safety. The authors provide a comparative analysis of methods supporting SOTIF, evaluating their effectiveness and practical applicability. Additionally, the paper incorporates supplementary insights from recent publications beyond the initial 2023 cutoff to address identified gaps, offering a more current perspective on emerging solutions. The significance of this work lies in its structured synthesis of the fragmented literature on SOTIF, providing a clear overview of the current state of knowledge and methodological approaches. By identifying specific research gaps, the paper proposes future research directions, including the development of frameworks for modeling SOTIF scenarios, generating test cases, and addressing uncertainties in machine learning-based perception algorithms. The study concludes that ensuring SOTIF requires rigorous verification and validation, including system modifications, redundancy measures, and fail-safe mechanisms, to mitigate risks associated with functional insufficiencies in automated driving systems.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | pdftotext | — | — | 4 | 2026-08-10 |
| clean | success | clean | — | — | 2 | 2026-08-10 |
| chunk | success | chunk | — | — | 2 | 2026-08-10 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 2 | 2026-08-10 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 17 | 2026-08-11 |
| verify | success | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Applied Guidance: standards test procedures
- Methodological Resource: tool software
- Synthesis & Review: research agenda