Private or On-Demand Autonomous Vehicles? Modeling Public Interest Using a Multivariate Model

Abstract

With the likely future of autonomous vehicles (AVs) as private, ride-hailing, and pooled vehicles, it is important to consider all forms of AVs when estimating the impacts of automation on travel behavior. To aid this, this study jointly models the public interest in three forms of AVs (owning, ride-hailing, and using pooled services) and compares the interests in owning versus ride-hailing AVs using a combination of structural equation modeling and multivariate ordered probit modeling frameworks. Using the 2019 California Vehicle Survey data, we estimate the impacts of several exogenous and latent variables on all forms of AV adoption. We find that the individual, household, travel-related, and built-environment factors are related to different forms of AV adoption directly and indirectly through attitudes toward human and automated driving. We also report that human and automated driving sentiments have the highest impact on interest in owning an AV compared to interest in ride-hailing and using pooled AVs. We discuss several policy implications by calculating the pseudo-elasticity effects of exogenous variables and the sensitivities of the impacts on latent variables on different forms of AV adoption. For example, public interest in owning private AVs can be increased by more than 7% by making them familiar with autonomous technology.