An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigation

• URL: http://arxiv.org/abs/2510.07825v1
• Date: Thu, 09 Oct 2025 06:14:29 GMT
• Title: An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigation
• Authors: Yuping Zhou, Siqi Lai, Jindong Han, Hao Liu,
• Abstract summary: Multi-vehicle dynamic navigation requires simultaneously routing large fleets under evolving traffic conditions.<n>Existing path search algorithms and reinforcement learning methods struggle to scale to city-wide networks.<n>We propose CityNav, a hierarchical, LLM-powered framework for large-scale multi-vehicle navigation.
• Score: 10.549493962440804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rise of Internet of Vehicles (IoV) technologies is transforming traffic management from isolated control to a collective, multi-vehicle process. At the heart of this shift is multi-vehicle dynamic navigation, which requires simultaneously routing large fleets under evolving traffic conditions. Existing path search algorithms and reinforcement learning methods struggle to scale to city-wide networks, often failing to capture the nonlinear, stochastic, and coupled dynamics of urban traffic. To address these challenges, we propose CityNav, a hierarchical, LLM-powered framework for large-scale multi-vehicle navigation. CityNav integrates a global traffic allocation agent, which coordinates strategic traffic flow distribution across regions, with local navigation agents that generate locally adaptive routes aligned with global directives. To enable effective cooperation, we introduce a cooperative reasoning optimization mechanism, in which agents are jointly trained with a dual-reward structure: individual rewards promote per-vehicle efficiency, while shared rewards encourage network-wide coordination and congestion reduction. Extensive experiments on four real-world road networks of varying scales (up to 1.6 million roads and 430,000 intersections) and traffic datasets demonstrate that CityNav consistently outperforms nine classical path search and RL-based baselines in city-scale travel efficiency and congestion mitigation. Our results highlight the potential of LLMs to enable scalable, adaptive, and cooperative city-wide traffic navigation, providing a foundation for intelligent, large-scale vehicle routing in complex urban environments. Our project is available at https://github.com/usail-hkust/CityNav.

Related papers

• Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing [1.4273866043218153]
  We address dynamic vehicle routing through a multi-agent reinforcement learning (MARL) framework for coordinated, network-aware fleet navigation.<n>We first propose Adaptive Navigation (AN), a decentralized MARL model where each intersection agent provides routing guidance based on local traffic and neighborhood state.<n>To improve scalability in large networks, we further propose Hierarchical Hub-based Adaptive Navigation (HHAN), an extension of AN that assigns agents only to key intersections (hubs)<n> Experiments on synthetic grids and real urban maps (Toronto, Manhattan) show that AN reduces average travel time versus SPF and learning baselines, maintaining 100% routing success.
  arXiv  Detail & Related papers  (2025-10-30T02:49:46Z)
• Origin-Destination Pattern Effects on Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning [7.813738581616868]
  Large-scale mixed traffic control, involving both human-driven and robotic vehicles, remains underexplored.<n>We propose a decentralized multi-agent reinforcement learning framework for managing large-scale mixed traffic networks.<n>We evaluate our approach on a real-world network of 14 intersections in Colorado Springs, Colorado, USA.
  arXiv  Detail & Related papers  (2025-05-19T01:36:05Z)
• Neighbor-Aware Reinforcement Learning for Mixed Traffic Optimization in Large-scale Networks [1.9413548770753521]
  This paper proposes a reinforcement learning framework for coordinating mixed traffic across interconnected intersections.<n>Our key contribution is a neighbor-aware reward mechanism that enables RVs to maintain balanced distribution across the network.<n>Results show that our method reduces average waiting times by 39.2% compared to the state-of-the-art single-intersection control policy.
  arXiv  Detail & Related papers  (2024-12-17T07:35:56Z)
• TransferLight: Zero-Shot Traffic Signal Control on any Road-Network [0.6274767633959003]
  TransferLight is a novel framework designed for robust generalization across road-networks.<n>Our hierarchical, heterogeneous, and directed graph neural network architecture effectively captures granular traffic dynamics.<n>We develop a single, weight-tied policy that scales zero-shot to any road network without re-training.
  arXiv  Detail & Related papers  (2024-12-12T20:52:12Z)
• CityLight: A Neighborhood-inclusive Universal Model for Coordinated City-scale Traffic Signal Control [23.5766158697276]
  CityLight learns a universal policy based on representations obtained with two major modules.<n>Experiments on five city-scale datasets, ranging from 97 to 13,952 intersections, confirm the efficacy of CityLight.
  arXiv  Detail & Related papers  (2024-06-04T09:10:14Z)
• Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots [50.02055068660255]
  Navigating urban environments poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we develop a versatile locomotion controller. Our controllers are integrated into a large-scale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain.
  arXiv  Detail & Related papers  (2024-05-03T00:29:20Z)
• Convergence of Communications, Control, and Machine Learning for Secure and Autonomous Vehicle Navigation [78.60496411542549]
  Connected and autonomous vehicles (CAVs) can reduce human errors in traffic accidents, increase road efficiency, and execute various tasks. Reaping these benefits requires CAVs to autonomously navigate to target destinations. This article proposes solutions using the convergence of communication theory, control theory, and machine learning to enable effective and secure CAV navigation.
  arXiv  Detail & Related papers  (2023-07-05T21:38:36Z)
• DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback [109.84667902348498]
  Traffic Signal Control (TSC) aims to reduce the average travel time of vehicles in a road network. Most prior TSC methods leverage deep reinforcement learning to search for a control policy. We propose DenseLight, a novel RL-based TSC method that employs an unbiased reward function to provide dense feedback on policy effectiveness.
  arXiv  Detail & Related papers  (2023-06-13T05:58:57Z)
• A Novel Multi-Agent Deep RL Approach for Traffic Signal Control [13.927155702352131]
  We propose a Friend-Deep Q-network (Friend-DQN) approach for multiple traffic signal control in urban networks. In particular, the cooperation between multiple agents can reduce the state-action space and thus speed up the convergence.
  arXiv  Detail & Related papers  (2023-06-05T08:20:37Z)
• Road Network Guided Fine-Grained Urban Traffic Flow Inference [108.64631590347352]
  Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem. We propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that exploits the prior knowledge of road networks. Our method can generate high-quality fine-grained traffic flow maps.
  arXiv  Detail & Related papers  (2021-09-29T07:51:49Z)
• Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms [57.21078336887961]
  Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day. We propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks.
  arXiv  Detail & Related papers  (2021-05-18T19:22:24Z)
• End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning [63.56464608571663]
  Navigating through intersections is one of the main challenging tasks for an autonomous vehicle. In this work, we focus on the implementation of a system able to navigate through intersections where only traffic signs are provided. We propose a multi-agent system using a continuous, model-free Deep Reinforcement Learning algorithm used to train a neural network for predicting both the acceleration and the steering angle at each time step.
  arXiv  Detail & Related papers  (2021-04-28T07:54:40Z)
• IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control [4.273991039651846]
  Scaling adaptive traffic-signal control involves dealing with state and action spaces. We introduce Inductive Graph Reinforcement Learning (IG-RL) based on graph-convolutional networks. Our model can generalize to new road networks, traffic distributions, and traffic regimes.
  arXiv  Detail & Related papers  (2020-03-06T17:17:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.