When Simulator Meets Natural Deviation: A Study on Deviations in Simulation-based ADS Testing
Bibliographic record
Abstract
Designing efficient testing for Autonomous Driving Systems (ADS) presents a crucial challenge in ensuring their quality. Thorough tests are the keys to their successful deployment in real-world scenarios. However, real-world testing for ADS is usually expensive and hard to scale. Meanwhile, simulation-based testing has gained popularity due to its flexibility and cost-effectiveness. Unfortunately, there exist certain limitations in simulation-based testing. The inherent hardware uncertainty typically impacts the robustness of ADS in real-world contexts. Nevertheless, current approaches often neglect this crucial factor and assume the hardware is perfect. To bridge this gap, we initiate an early step and design a test pipeline for simulation-based testing with possible natural deviations. We validate the effectiveness of our testing pipeline on a multi-model ADS in 11 typical scenarios, each containing more than 60 deviations. Through experiments, we identify that both AI models and traditional software systems of ADS are not robust against natural deviation.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".