Towards a skill- and ability-based development process for self-aware automated road vehicles
DOI: 10.1109/itsc.2017.8317814
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 addresses the challenge of developing safe, fully automated vehicles (SAE Levels 3+) by proposing a skill- and ability-based development process compliant with ISO 26262. Traditional design methods are insufficient for the vast variety of scenarios encountered by automated vehicles, particularly because the human driver is not available as a fallback. Consequently, vehicles must be "self-aware," monitoring their internal state and performance limits in real-time. The authors combine insights from two research projects: *Unmanned Protective Vehicle for Highway Hard Shoulder Road Works* (aFAS), which serves as a use case for the design phase, and *Controlling Concurrent Change* (CCC), which focuses on runtime integration and monitoring mechanisms. The methodology centers on modeling the vehicle’s functional behavior using directed acyclic graphs of "skills" and "abilities." A "skill" is defined as an activity required to fulfill system goals, while an "ability" describes the quality level of that activity based on internal properties and the operational situation. During the development phase, skill graphs are used to derive functional safety requirements from Hazard Analysis and Risk Assessment (HARA). For the aFAS project, which involves an unmanned protective vehicle operating on highway hard shoulders, the authors identified hazardous scenarios, such as the vehicle entering moving traffic. They derived safety goals, such as limiting steering lock to 3 degrees (ASIL D) or maintaining a safe distance to lane markings (ASIL B), and translated these into technical requirements for specific skills, such as lateral dynamics control. In the operational phase, skill graphs are transformed into ability graphs for runtime monitoring. The authors propose using ontologies to map abilities to software components and define performance metrics. These metrics aggregate data from sensors and actuators to assess the vehicle’s current performance level. For example, to ensure the vehicle maintains a safe distance from lane markings, the system monitors the overshoot of control algorithms and the variance of perception estimates. If the variance exceeds specified bounds or perception data is invalid, the system can detect degradation. This approach allows for the composition of atomic metrics into higher-level composed metrics, enabling the vehicle to assess its own capabilities and adhere to safety goals dynamically. The significance of this work lies in providing a structured framework for integrating functional safety development with runtime self-awareness. By linking high-level safety goals to low-level technical metrics through skill and ability graphs, the approach ensures that automated vehicles can continuously verify their performance against safety requirements. This facilitates the development of systems that can operate without human supervision by actively monitoring their internal states and external behaviors, thereby addressing the critical safety challenges associated with higher levels of automation.
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 | 2026-06-20 |
| archive | success | unpaywall | — | — | 2 | 2026-06-26 |
| extract | success | pdftotext | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | success | openalex | — | — | 1 | 2026-06-26 |
| promote | success | — | — | — | 1 | 2026-06-20 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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
- Theoretical Contribution: conceptual framework, computational model