Bi-level RL-Heuristic Optimization for Real-world Winter Road Maintenance

• URL: http://arxiv.org/abs/2602.24097v1
• Date: Fri, 27 Feb 2026 15:37:35 GMT
• Title: Bi-level RL-Heuristic Optimization for Real-world Winter Road Maintenance
• Authors: Yue Xie, Zizhen Xu, William Beazley, Fumiya Iida,
• Abstract summary: Winter road maintenance is critical for ensuring public safety and reducing environmental impacts.<n>Existing methods struggle to manage large-scale routing problems effectively and mostly reply on human decision.<n>This study presents a novel, scalable bi-level optimization framework, validated on real operational data on UK strategic road networks.
• Score: 3.7856931422411346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Winter road maintenance is critical for ensuring public safety and reducing environmental impacts, yet existing methods struggle to manage large-scale routing problems effectively and mostly reply on human decision. This study presents a novel, scalable bi-level optimization framework, validated on real operational data on UK strategic road networks (M25, M6, A1), including interconnected local road networks in surrounding areas for vehicle traversing, as part of the highway operator's efforts to solve existing planning challenges. At the upper level, a reinforcement learning (RL) agent strategically partitions the road network into manageable clusters and optimally allocates resources from multiple depots. At the lower level, a multi-objective vehicle routing problem (VRP) is solved within each cluster, minimizing the maximum vehicle travel time and total carbon emissions. Unlike existing approaches, our method handles large-scale, real-world networks efficiently, explicitly incorporating vehicle-specific constraints, depot capacities, and road segment requirements. Results demonstrate significant improvements, including balanced workloads, reduced maximum travel times below the targeted two-hour threshold, lower emissions, and substantial cost savings. This study illustrates how advanced AI-driven bi-level optimization can directly enhance operational decision-making in real-world transportation and logistics.

Related papers

• Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms [53.75036695728983]
  Vehicle Routing Problems (VRP) are a fundamental NP-hard challenge in Evolutionary optimization.<n>We introduce an optimization framework where a reinforcement learning agent is trained on prior instances and quickly generates initial solutions.<n>This framework consistently outperforms current state-of-the-art solvers across various time budgets.
  arXiv  Detail & Related papers  (2025-04-08T15:21:01Z)
• Multi-objective Optimal Roadside Units Deployment in Urban Vehicular Networks [7.951541004150428]
  The significance of transportation efficiency, safety, and related services is increasing in urban vehicular networks. Within such networks, roadside units (RSUs) serve as intermediates in facilitating communication. In urban environments, the presence of various obstacles, such as buildings, gardens, lakes, and other infrastructure, poses challenges for the deployment of RSUs.
  arXiv  Detail & Related papers  (2024-01-14T05:02:12Z)
• TOP-Former: A Multi-Agent Transformer Approach for the Team Orienteering Problem [47.40841984849682]
  Route planning for a fleet of vehicles is an important task in applications such as package delivery, surveillance, or transportation.<n>We introduce TOP-Former, a multi-agent route planning neural network designed to efficiently and accurately solve the Team Orienteering Problem.
  arXiv  Detail & Related papers  (2023-11-30T16:10:35Z)
• Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning [55.08287089554127]
  Open Radio Access Network systems, with their base stations (vBSs), offer operators the benefits of increased flexibility, reduced costs, vendor diversity, and interoperability.<n>We propose an online learning algorithm that balances the effective throughput and vBS energy consumption, even under unforeseeable and "challenging'' environments.<n>We prove the proposed solutions achieve sub-linear regret, providing zero average optimality gap even in challenging environments.
  arXiv  Detail & Related papers  (2023-09-04T17:30:21Z)
• Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem [40.50169360761464]
  Collaborative vehicle routing has been proposed as a solution to increase efficiency. Current operations research methods suffer from non-linear scaling with increasing problem size. We develop a reinforcement learning model to solve the three-dimensional loading capacitated vehicle routing problem in approximately linear time.
  arXiv  Detail & Related papers  (2023-07-22T18:05:28Z)
• 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 Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning [6.756220853104791]
  We tackle the interdependent problems of service task placement and scaling of edge resources.<n>We propose a new Deep Reinforcement Learning (DRL) approach that operates in hybrid action spaces.<n>We evaluate the performance of DHPG using simulations with a real-world C-V2N traffic dataset.
  arXiv  Detail & Related papers  (2023-05-16T22:19:19Z)
• LCS-TF: Multi-Agent Deep Reinforcement Learning-Based Intelligent Lane-Change System for Improving Traffic Flow [16.34175752810212]
  Existing intelligent lane-change solutions have primarily focused on optimizing the performance of the ego vehicle. Recent research has seen an increased interest in multi-agent reinforcement learning (MARL)-based approaches. We present a novel hybrid MARL-based intelligent lane-change system for AVs designed to jointly optimize the local performance for the ego vehicle.
  arXiv  Detail & Related papers  (2023-03-16T04:03:17Z)
• An ASP Framework for Efficient Urban Traffic Optimization [0.0]
  This paper presents a framework which allows to efficiently simulate and optimize traffic flow in a large roads' network with hundreds of vehicles. The framework leverages on an Answer Set Programming (ASP) encoding to formally describe the movements of vehicles inside a network. It is then possible to optimize the routes of vehicles inside the network to reduce a range of relevant metrics.
  arXiv  Detail & Related papers  (2022-08-05T10:50:38Z)
• AI-aided Traffic Control Scheme for M2M Communications in the Internet of Vehicles [61.21359293642559]
  The dynamics of traffic and the heterogeneous requirements of different IoV applications are not considered in most existing studies. We consider a hybrid traffic control scheme and use proximal policy optimization (PPO) method to tackle it.
  arXiv  Detail & Related papers  (2022-03-05T10:54:05Z)
• Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning [1.6752182911522522]
  Frequent lane changes during congestion at freeway bottlenecks such as merge and weaving areas further reduce roadway capacity. The emergence of deep reinforcement learning (RL) and connected and automated vehicle technology provides a possible solution to improve mobility and energy efficiency at freeway bottlenecks through cooperative lane changing. In this study, a decentralized cooperative lane-changing controller was developed using a multi-agent deep RL paradigm. The results of this study show that cooperative lane changing enabled by multi-agent deep RL yields superior performance to human drivers in term of traffic throughput, vehicle speed, number of stops per vehicle, vehicle fuel efficiency, and emissions.
  arXiv  Detail & Related papers  (2021-10-05T18:29:13Z)
• 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)

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.