Semi-on-Demand Transit Feeders with Shared Autonomous Vehicles and Reinforcement-Learning-Based Zonal Dispatching Control

2025-09-01

AI Summary

To address the contradiction between poor public transit accessibility, high operational costs of fixed-route services, and low efficiency of demand-responsive transit in low-density areas, this paper proposes a “fixed + flexible” semi-on-demand feeder bus model: vehicles operate along a fixed route from the origin station and then enter a pre-defined flexible zone to provide on-demand boarding and alighting. Innovatively, a zonal reinforcement learning (RL) dispatching mechanism based on Proximal Policy Optimization (PPO) is introduced, integrated with multi-agent simulation for dynamic vehicle assignment. In a real-world simulation using Munich’s transit network, the proposed model serves 16% more passengers than conventional fixed-route service while increasing generalized cost by only 13%. Incorporating the PPO-based RL dispatcher further improves system efficiency by 2.4%. The approach effectively mitigates the first- and last-mile problem and establishes a scalable, shared-autonomous-vehicle (SAV)-enabled cooperative operation paradigm for sustainable mobility in low-density regions.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Application Domains: Transportation

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper develops a semi-on-demand transit feeder service using shared autonomous vehicles (SAVs) and zonal dispatching control based on reinforcement learning (RL). This service combines the cost-effectiveness of fixed-route transit with the adaptability of demand-responsive transport to improve accessibility in lower-density areas. Departing from the terminus, SAVs first make scheduled fixed stops, then offer on-demand pick-ups and drop-offs in a pre-determined flexible-route area. Our deep RL model dynamically assigns vehicles to subdivided flexible-route zones in response to real-time demand fluctuations and operations, using a policy gradient algorithm - Proximal Policy Optimization. The methodology is demonstrated through agent-based simulations on a real-world bus route in Munich, Germany. Results show that after efficient training of the RL model, the semi-on-demand service with dynamic zonal control serves 16% more passengers at 13% higher generalized costs on average compared to traditional fixed-route service. The efficiency gain brought by RL control brings 2.4% more passengers at 1.4% higher costs. This study not only showcases the potential of integrating SAV feeders and machine learning techniques into public transit, but also sets the groundwork for further innovations in addressing first-mile-last-mile problems in multimodal transit systems.

Problem

• Developing semi-on-demand transit feeders using autonomous vehicles
• Improving accessibility in lower-density areas with adaptive transport
• Addressing first-mile-last-mile problems in multimodal transit systems

Innovation

• Shared autonomous vehicles for transit feeders
• Reinforcement learning zonal dispatching control
• Dynamic assignment to zones using PPO