A Hierarchical Framework for the Management of Carpooling Using Autonomous Vehicles

The growing diffusion of Autonomous Vehicles (AVs) is reshaping urban mobility by enabling new forms of intelligent transportation, such as shared and on-demand services. Among these, carpooling with AVs represents a promising solution to reduce traffic congestion, emissions, and operational costs.This paper presents a Hierarchical framework for carpooling management based on two strategies: i) a Deep Reinforcement Learning (DRL) model to optimize the sequence of pick-ups and drop-offs performed by AVs, and ii) a rerouting algorithm for selecting the best route considering dynamic traffic conditions. The carpooling problem is formalized using the Markov Decision Process framework. The proposed approach is implemented using the Proximal Policy Optimization algorithm and validated through simulations in the Simulation of Urban Mobility (SUMO) environment.As a case study, the cities of Bari (Italy) and Tampere (Finland) are analyzed to assess model performance in real urban scenarios. Results show that the proposed method improves route efficiency and supports the development of intelligent and sustainable mobility systems.