A Framework for Automated Driving System Testable Cases and Scenarios
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, sponsored by the National Highway Traffic Safety Administration (NHTSA), addresses the need for a structured framework to test and evaluate Automated Driving Systems (ADS) in light-duty vehicles. The research was motivated by the rapid development of ADS technologies, specifically those operating at SAE Levels 3 through 5, and the necessity to establish preliminary testing protocols to ensure safety and mobility improvements. The primary goal was to develop a sample test framework for ADS features expected to reach the market in the near to mid-term future. The methodology involved a multi-step process beginning with a comprehensive literature review of technical journals, press releases, and conference proceedings to identify concept ADS features. Twenty-four conceptual features were identified and categorized into seven generic groups, such as "L4 Highly Automated Vehicle/Transportation Network Company" and "L3 Conditional Automated Traffic Jam Drive." Three specific features were selected for detailed analysis: L3 Conditional Automated Traffic Jam Drive, L3 Conditional Automated Highway Drive, and L4 Highly Automated Vehicle/TNC. The researchers defined the Operational Design Domain (ODD) for these features using a hierarchical taxonomy comprising physical infrastructure, operational constraints, objects, connectivity, environmental conditions, and zones. They also analyzed Object and Event Detection and Response (OEDR) capabilities by mapping tactical maneuver behaviors and OEDR behaviors to specific objects and events. Additionally, a high-level Failure Mode and Effects Analysis (FMEA) was conducted to identify potential failure modes and mitigation strategies, including fail-safe and fail-operational techniques. The findings established a multidimensional test scenario framework structured as a matrix with four principal elements: Tactical Maneuver Behavior, ODD Elements, OEDR Behavior, and Failure Mode Behaviors. The report identified three main components of a testing architecture: Modeling and Simulation (M&S), Closed-Track Testing, and Open-Road Testing, evaluating the advantages and disadvantages of each. Specific baseline ODDs and OEDR capabilities were defined for the three selected ADS features, detailing expected hazards and sporadic events. The FMEA revealed that potential failures often stemmed from lack of information or poor information quality, leading to significant risks such as collisions. The study also outlined specific failure mitigation strategies, such as transitioning control to a fallback-ready user, safely stopping, or employing adaptive compensation techniques like weighting data from complementary sensors. The significance of this work lies in providing a foundational framework for the development of industry standards for ADS testing. By defining clear ODD taxonomies and OEDR capabilities, the report offers a structured approach for developers to delineate their systems' operational boundaries. The proposed test scenario framework allows for flexible and comprehensive evaluation of ADS performance across various conditions and failure modes. This framework supports the validation and verification of ADS technologies, helping to ensure that these systems can safely perform the dynamic driving task and respond appropriately to objects and events within their designated operational domains.
Key finding
The study proposes a multidimensional test scenario matrix that combines tactical maneuver behaviors, operational design domain elements, object and event detection and response capabilities, and failure mode behaviors to structure ADS validation.
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.
- driverless ads
- situational awareness
- automation surprise
- odd communication
- naturalistic crash near crash
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: dataset resource
- Theoretical Contribution: conceptual framework