Civil Engineering Faculty Publications and Presentations

Document Type

Report

Publication Date

8-19-2025

Abstract

This study develops a Dynamic Bayesian Network (DBN) framework to examine how public confidence in autonomous vehicle (AV) safety and willingness-to-ride respond to policy interventions in crash-imminent pedestrian–passenger prioritization scenarios. Using stated preferences survey data from San Francisco (SF) and San Antonio (SA), the model integrates baseline attitudes, socio-demographic factors, and policy conditions to simulate both intra-slice and inter-slice dependencies. Results from empirical-mix simulations indicate that SF respondents, despite having higher baseline confidence and willingness-to-ride, exhibit greater sensitivity to policies prioritizing pedestrians, with significant declines across all scenarios. By contrast, SA respondents show comparatively stable and modestly positive shifts, particularly when policies favor passengers. Stratified analyses reveal heterogeneity so that policies such as pedestrian prioritization amplify existing differences across baseline confidence groups, while others, like prioritization by child presence or group size, promote convergence toward midscale attitudes. The findings underscore the value of DBNs in capturing causal and temporal dynamics in AV acceptance and highlight important city-level and attitudinal differences in policy responsiveness.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.