mlsanityData to 14 Oct 2026

Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator

arXiv 2506.07980 ↗First posted 9 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Realistic urban traffic simulation is essential for sustainable urban planning and the development of intelligent transportation systems. However, generating high-fidelity, time-varying traffic profiles that accurately reflect real-world conditions, especially in large-scale scenarios, remains a major challenge. Existing methods often suffer from limitations in accuracy, scalability, or raise privacy concerns due to centralized data processing. This work introduces DesRUTGe (Decentralized Realistic Urban Traffic Generator), a novel framework that integrates Deep Reinforcement Learning (DRL) agents with the SUMO simulator to generate realistic 24-hour traffic patterns. A key innovation of DesRUTGe is its use of Decentralized Federated Learning (DFL), wherein each traffic detector and its corresponding urban zone function as an independent learning node. These nodes train local DRL models using minimal historical data and collaboratively refine their performance by exchanging model parameters with selected peers (e.g., geographically adjacent zones), without requiring a central coordinator. Evaluated using real-world data from the city of Barcelona, DesRUTGe outperforms standard SUMO-based tools such as RouteSampler, as well as other centralized learning approaches, by delivering more accurate and privacy-preserving traffic pattern generation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 77 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

30 of 77 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  8. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  9. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  10. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  11. 2013On the Convergence of Decentralized Gradient Descentcited by 159
  12. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
18 more
  1. 2022TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarioscited by 106
  2. 2020A Blockchain-based Decentralized Federated Learning Framework with Committee Consensuscited by 84
  3. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 84
  4. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 83
  5. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 81
  6. 2019Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networkscited by 79
  7. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 57
  8. 2021Decentralized Federated Learning: Balancing Communication and Computing Costscited by 55
  9. 2024Byzantine-Robust Decentralized Federated Learningcited by 48
  10. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
  11. 2016On Nonconvex Decentralized Gradient Descentcited by 42
  12. 2019SUMMIT: A Simulator for Urban Driving in Massive Mixed Trafficcited by 40
  13. 2023Reinforcement Learning with Human Feedback for Realistic Traffic Simulationcited by 21
  14. 2020Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDERcited by 19
  15. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  16. 2024Byzantine-Robust Aggregation for Securing Decentralized Federated Learningcited by 7
  17. 2024Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentationcited by 1
  18. 2025Federated Hierarchical Reinforcement Learning for Adaptive Traffic Signal Controlcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SUMO-MCP: Leveraging the Model Context Protocol for Autonomous Traffic Simulation and Optimization
  2. 2024Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation
  3. 2026MoE Enhanced Federated Learning for Spatiotemporal Prediction
  4. 2022Traffic Management of Autonomous Vehicles using Policy Based Deep Reinforcement Learning and Intelligent Routing
  5. 2025Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning
  6. 2026CROSS: A Mixture-of-Experts Reinforcement Learning Framework for Generalizable Large-Scale Traffic Signal Control
  7. 2025Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark
  8. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving