Applying Machine Learning to Explore Feelings about Sharing the Road with Autonomous Vehicles as a Bicyclist or as a Pedestrian

The current literature on public perceptions of autonomous vehicles focuses potential users and the target market. However, need to operate in a mixed traffic condition, it is essential consider road users, especially vulnerable users. This paper builds explicitly limitations previous studies that did not include wide range who often receive less priority. Therefore, this considers towards sharing roads with vehicles. data were collected from 795 people. Extreme gradient boosting (XGBoost) random forests are used select most influential independent variables. Then, decision tree-based model explore effects selected effective variables respondents approve use streets as proving ground for results show effect injuries fatalities, being safe share vehicles, Elaine Herzberg accident its outcome, maximum speed when operating can be by authorities, companies, policymakers, planners, other stakeholders.