Automated Design Optimization of Side View Mirror Geometries for Improved Autonomous Sensor and Vehicle Soiling Performance
Bibliographic record
Abstract
<div class="section abstract"><div class="htmlview paragraph">The use of sensors in advanced driver-assistance systems (ADAS) and autonomous vehicles has been accelerating over the past few years largely driven by regulatory and consumer interest in safety applications. These sensors help to prevent accidents and protect drivers by assisting with the monitoring, warning, braking, and steering tasks. As several unfortunate examples have highlighted these valuable systems can reduce safety if the sensors are not operating un-impaired. Planning for harsh weather environments is critical to the success of these systems. This study presents a fully automated workflow for an industrial side mirror geometry optimization for improved sensor performance under soiling conditions. The methodology includes CAD parametrization, multiphase simulation setup, intelligent design optimization and a detailed result analysis. All relevant aspects like external flow, geometrical fidelity and multiphase interaction are considered. A source term is applied to a fluid film model that approximates the effect of raindrops accumulating on the side view mirror. The average fluid film thickness on the camera lens is monitored and a numerical integration of the mean thickness vs time is used to compare designs. The parametric mirror geometry modifies the depth, location, and shape of trench surrounding the camera mound. This design concept is intended to capture and redirect the fluid film to avoid contact with the camera lens. The parametrized, lower part of the side mirror is modified by the optimization algorithm resulting in a 26% decrease in the time integral of the film thickness on the camera lens.</div></div>
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".