Autonomous Vehicle Safety Assessment with Fully Quantified ODDs
Bibliographic record
Abstract
We are in the midst of a vehicle safety revolution. Current vehicle safety standards, best practices, and approaches are not adequate to ensure the safety of an Automated Vehicle (AV), the motoring public, and vulnerable road users. Continued application of these nascent technologies prompts the question: How safe is safe enough and how do we know that these systems can handle inherent risks of a given deployment area? Current practices are very focused on vehicle safety elements. In fact, there is currently only one published safety standard, specifically for AVs [1], though there are instances where some vehicle system safety standards are being adapted for AV application and some safety standards from other industries (e.g. aerospace and nuclear) are being considered. Specific guidelines for AV safety metrics and AV safety performance are currently in the development stages and once published will require time to be fully understood, thresholds defined, and data collected and accepted by the AV community. A holistic approach to safety that considers all aspects of a safe AV deployment beyond increasing levels of vehicle technology is crucial. Included in this holistic approach, as a foundational element, is a fundamentally new way of assessing and quantifying risks within the Operational Design Domain (ODD). This is produced by breaking down the risk of a given ODD as a sum over the risk of component scenarios which make up the ODD. This means ODDs are fully specified and not defined by subjective assumptions. With no single standard, best practice, or guideline that covers AV safety in a holistic manner, an assessment process including a fully quantified ODD is seen as the most effective way to cover all aspects of safety, including the environment, management practices, and the vehicles.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".