An Approach for the Selection and Description of Elements Used to Define Driving Scenarios – Part II
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This report, titled "An Approach for the Selection and Description of Elements Used to Define Driving Scenarios – Part II," addresses the need for standardized, reproducible, and traceable methods for describing driving scenarios used in testing Automated Driving Systems (ADS). Building upon previous research that identified elements for five specific scenarios, this study aims to expand that framework by analyzing six additional scenarios. The motivation stems from the necessity to cover a broader range of behavioral competencies and crash typologies relevant to ADS development, ensuring that simulation and testing frameworks can accurately represent complex real-world interactions. The methodology involved selecting six new scenarios from diverse data sources, including driving databases, crash databases, California DMV reports, National Transportation Safety Board (NTSB) investigations, and behavioral competency frameworks not covered in prior work. The selected scenarios are: suddenly revealed stopped vehicle, straight crossing path, opposing traffic, parking/reversing, encountering construction zones, and encountering special vehicles (emergency vehicles and school buses). The authors analyzed these scenarios to identify necessary elements and properties, focusing on "ground truth" information relevant to the planning and control subsystems of ADS, while excluding sensing and perception complexities. The analysis categorized elements into initialization, environmental factors, dynamic actors, traffic, and ADS status. The findings resulted in the expansion of the preliminary list of scenario elements and properties. Specifically, the study added three new elements: "parking lot" under road properties, and "special vehicle" and "special pedestrian" under dynamic actors. Additionally, "ADS Mode" was added to the ADS status category. Each new element was accompanied by specific properties to facilitate detailed scenario parametrization. For instance, the parking/reversing scenario required new properties related to parking spot identification and maneuver completion, while the construction zone scenario necessitated elements describing traffic control devices and road map changes. The report provides a consolidated list of these elements and properties, detailing how they can be parameterized to create specific, repeatable test cases. The significance of this work lies in its contribution to the standardization of ADS testing protocols. By providing a more comprehensive set of elements and properties, the report facilitates better data translation, scenario exchange, and reproducibility across different simulation tools and testing environments. This expanded framework supports the industry's need for rigorous validation of ADS performance across a wider variety of driving conditions and interactions, ultimately aiding in the safe deployment of automated vehicles. The report serves as a technical reference for defining scenario test cases that are unambiguous and traceable, addressing gaps in previous scenario description efforts.
Key finding
The analysis of six additional driving scenarios expanded the preliminary framework by introducing new elements for parking lots, special vehicles, and ADS modes, thereby creating a more comprehensive set of properties for scenario description.
Methodology
review
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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- crash typology
- situational awareness
- naturalistic crash near crash
- pre crash contributing factors
- automation surprise
- anticipation
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).
- Methodological Resource: dataset resource
- Theoretical Contribution: conceptual framework, computational model