Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Vehicle Dispatching and Routing of On-Demand Intercity Ride-Pooling Services: A Multi-Agent Hierarchical Reinforcement Learning Approach

Jinhua Si, Fang He, Xi Lin, Xindi Tang

TL;DR

The paper tackles online fleet operations for intercity ride-pooling within city clusters by separating the problem into a long-horizon, multi-agent resource-allocation layer and a short-horizon, line-level routing layer. It introduces Multi-agent Feudal Networks (MFuN) as the upper-level controller to cooperatively allocate idle vehicles to intercity lines and Adaptive Large Neighborhood Search (ALNS) as the lower-level routing heuristic to service orders within each line. The approach is evaluated on toy networks and a realistic Xiamen dataset, showing that MFuN-ALNS improves average daily profit and order fulfillment compared to baselines, with stronger gains under supply-demand imbalances. The framework demonstrates scalable, non-myopic decision-making for intercity ride-pooling in city clusters, with practical potential for real-time deployment and future extensions to pricing and broader intercity planning.

Abstract

The integrated development of city clusters has given rise to an increasing demand for intercity travel. Intercity ride-pooling service exhibits considerable potential in upgrading traditional intercity bus services by implementing demand-responsive enhancements. Nevertheless, its online operations suffer the inherent complexities due to the coupling of vehicle resource allocation among cities and pooled-ride vehicle routing. To tackle these challenges, this study proposes a two-level framework designed to facilitate online fleet management. Specifically, a novel multi-agent feudal reinforcement learning model is proposed at the upper level of the framework to cooperatively assign idle vehicles to different intercity lines, while the lower level updates the routes of vehicles using an adaptive large neighborhood search heuristic. Numerical studies based on the realistic dataset of Xiamen and its surrounding cities in China show that the proposed framework effectively mitigates the supply and demand imbalances, and achieves significant improvement in both the average daily system profit and order fulfillment ratio.

Vehicle Dispatching and Routing of On-Demand Intercity Ride-Pooling Services: A Multi-Agent Hierarchical Reinforcement Learning Approach

TL;DR

The paper tackles online fleet operations for intercity ride-pooling within city clusters by separating the problem into a long-horizon, multi-agent resource-allocation layer and a short-horizon, line-level routing layer. It introduces Multi-agent Feudal Networks (MFuN) as the upper-level controller to cooperatively allocate idle vehicles to intercity lines and Adaptive Large Neighborhood Search (ALNS) as the lower-level routing heuristic to service orders within each line. The approach is evaluated on toy networks and a realistic Xiamen dataset, showing that MFuN-ALNS improves average daily profit and order fulfillment compared to baselines, with stronger gains under supply-demand imbalances. The framework demonstrates scalable, non-myopic decision-making for intercity ride-pooling in city clusters, with practical potential for real-time deployment and future extensions to pricing and broader intercity planning.

Abstract

The integrated development of city clusters has given rise to an increasing demand for intercity travel. Intercity ride-pooling service exhibits considerable potential in upgrading traditional intercity bus services by implementing demand-responsive enhancements. Nevertheless, its online operations suffer the inherent complexities due to the coupling of vehicle resource allocation among cities and pooled-ride vehicle routing. To tackle these challenges, this study proposes a two-level framework designed to facilitate online fleet management. Specifically, a novel multi-agent feudal reinforcement learning model is proposed at the upper level of the framework to cooperatively assign idle vehicles to different intercity lines, while the lower level updates the routes of vehicles using an adaptive large neighborhood search heuristic. Numerical studies based on the realistic dataset of Xiamen and its surrounding cities in China show that the proposed framework effectively mitigates the supply and demand imbalances, and achieves significant improvement in both the average daily system profit and order fulfillment ratio.
Paper Structure (23 sections, 11 equations, 22 figures, 2 algorithms)

This paper contains 23 sections, 11 equations, 22 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Modeling
  4. Problem settings
  5. Modeling framework
  6. The fleet dispatching model
  7. The vehicle routing model
  8. Solution Methodologies
  9. Upper level: Multi-agent Feudal Networks
  10. Model structure
  11. Learning methods
  12. Determine vehicle assignment
  13. Lower level: Adaptive large neighborhood search heuristic
  14. Numerical Experiments
  15. Comparative analysis of network architectures
  16. ...and 8 more sections

Figures (22)

  • Figure 1: Intercity passenger transport in a pooled-ride manner.
  • Figure 2: (a) Illustration of the dispatching horizons and matching intervals. (b) Interaction between two levels.
  • Figure 3: The fleet operational decision process for a network with one central city A and three surrounding cities B, C, and D.
  • Figure 4: Actor network structure of MFuN
  • Figure 5: The output of worker agent $u$
  • ...and 17 more figures