An investigation of supervised machine learning models for predicting drivers’ ethical decisions in autonomous vehicles
Bibliographic record
Abstract
Vehicle-pedestrian interactions in autonomous vehicles (AVs) present complex challenges that require advanced decision-making algorithms. Understanding the factors influencing ethical decision-making (EDM) in critical situations is essential as AVs become more prevalent. This study addresses a gap in AV research by using predictive analytics methods to develop models that assess decision-making outcomes under varying time pressures. We recruited 204 participants from North America, aged 18-30 years and 65 years and above, for an online experiment. Participants viewed video clips from a driving simulator that simulated ethical dilemmas. They had to decide whether the AV should stay in its lane or change lanes by pressing the spacebar. The principal component analysis identified age, distraction, and trust in automation as the key factors influencing decision-making. Several machine learning models were optimized to predict decision outcomes, with the Gaussian Naive Bayes model demonstrating strong performance across different time pressures. Feature importance analysis highlighted the significant roles of age and trust in automation. Partial dependence plots illustrated the interaction between these factors and their influence on decision-making outcomes under time constraints. These findings contribute to the development of personalized decision-making algorithms for AVs. Predictive analytics provides valuable insights into improving AV systems’ safety, trust, and ethical behavior by accounting for individual differences in decision-making. • Optimized machine learning models to predict drivers’ ethical decisions in autonomous vehicle-pedestrian interactions. • PCA identified age, distraction, and trust in automation as key factors in utilitarian decision-making. • Gaussian Naive Bayes performed optimum across different time constraints.
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 | 0.008 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".