Modelling autonomous vehicle parking: An agent-based simulation approach

Abstract

Autonomous vehicles (AVs) present a paradigm shift in addressing conventional parking challenges. Unlike human-driven vehicles, AVs can strategically park or cruise until summoned by users. Utilizing utility theory, the parking decision-making processes of AVs users are explored, taking into account constraints related to both cost and time. An agent-based simulation approach is adopted to construct an AV parking model, reflecting the complex dynamics of the parking decision process in the real world, where each user's choice has a ripple effect on traffic conditions, consequently affecting the feasible options for other users. The simulation experiments indicate that 11.50% of AVs gravitate towards parking lots near their destinations, while over 50% of AVs avoid public parking amenities altogether. This trend towards minimizing individual parking costs prompts AVs to undertake extended empty cruising, resulting in a significant increase of 48.18% in total vehicle mileage. Moreover, the pricing structure across various parking facilities and management dictates the parking preferences of AVs, establishing a nuanced trade-off between parking expenses and proximity for these vehicles.