mlsanityData to 7 Oct 2026

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

arXiv 2509.01883 ↗First posted 2 Sep 2025cs.LG cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 26 references that are in the map. First posted on arXiv 2 Sep 2025.

Builds on

11 of 26 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2020A Closer Look at Invalid Action Masking in Policy Gradient Algorithmscited by 160
  4. 2016OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networkscited by 109
  5. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 94
  6. 2021Reinforcement Learning for Ridesharing: An Extended Surveycited by 35
  7. 2019Enhanced Mobility With Connectivity and Automation: A Review of Shared Autonomous Vehicle Systemscited by 7
  8. 2022FleetPy: A Modular Open-Source Simulation Tool for Mobility On-Demand Servicescited by 1
  9. 2023Redesigning Large-Scale Multimodal Transit Networks with Shared Autonomous Mobility Servicescited by 1
  10. 2024Semi-on-Demand Hybrid Transit Route Design with Shared Autonomous Mobility Servicescited by 1
  11. 2024Autonomous Minibus Service with Semi-on-demand Routes in Grid Networkscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning
  2. 2025One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms
  3. 2020Flatland-RL : Multi-Agent Reinforcement Learning on Trains
  4. 2025URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
  5. 2026Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority
  6. 2025Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework
  7. 2025Impact of Collective Behaviors of Autonomous Vehicles on Urban Traffic Dynamics: A Multi-Agent Reinforcement Learning Approach
  8. 2023Adaptive Road Configurations for Improved Autonomous Vehicle-Pedestrian Interactions using Reinforcement Learning