mlsanityData to 14 Oct 2026

Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning

arXiv 2412.03925 ↗First posted 5 Dec 2024eess.SY cs.LG cs.SYcited by 1

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

Traffic simulations are commonly used to optimize urban traffic flow, with reinforcement learning (RL) showing promising potential for automated traffic signal control, particularly in intelligent transportation systems involving connected automated vehicles. Multi-agent reinforcement learning (MARL) is particularly effective for learning control strategies for traffic lights in a network using iterative simulations. However, existing methods often assume perfect vehicle detection, which overlooks real-world limitations related to infrastructure availability and sensor reliability. This study proposes a co-simulation framework integrating CARLA and SUMO, which combines high-fidelity 3D modeling with large-scale traffic flow simulation. Cameras mounted on traffic light poles within the CARLA environment use a YOLO-based computer vision system to detect and count vehicles, providing real-time traffic data as input for adaptive signal control in SUMO. MARL agents trained with four different reward structures leverage this visual feedback to optimize signal timings and improve network-wide traffic flow. Experiments in a multi-intersection test-bed demonstrate the effectiveness of the proposed MARL approach in enhancing traffic conditions using real-time camera based detection. The framework also evaluates the robustness of MARL under faulty or sparse sensing and compares the performance of YOLOv5 and YOLOv8 for vehicle detection. Results show that while better accuracy improves performance, MARL agents can still achieve significant improvements with imperfect detection, demonstrating scalability and adaptability for real-world scenarios.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 59 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

19 of 59 references.

References · 19

  1. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  2. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  3. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  4. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  5. 2019Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Drivingcited by 59
  6. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 52
  7. 2024ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObilitycited by 34
  8. 2017Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learningcited by 33
  9. 2019Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learningcited by 33
  10. 2019Learning an Interpretable Traffic Signal Control Policycited by 20
  11. 2020Cooperative Perception with Deep Reinforcement Learning for Connected Vehiclescited by 14
  12. 2021An Overview of Agent-based Traffic Simulatorscited by 11
7 more
  1. 2022Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Reviewcited by 7
  2. 2018Smoothing Traffic Flow via Control of Autonomous Vehiclescited by 6
  3. 2019A Reinforcement Learning Approach for Intelligent Traffic Signal Control at Urban Intersectionscited by 6
  4. 2024A Simple Framework Towards Vision-based Traffic Signal Control with Microscopic Simulationcited by 3
  5. 2024Field Deployment of Multi-Agent Reinforcement Learning Based Variable Speed Limit Controllerscited by 2
  6. 2016JADE, TraSMAPI and SUMO: A tool-chain for simulating traffic light controlcited by 1
  7. 2023Customized Co-Simulation Environment for Autonomous Driving Algorithm Development and Evaluationcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27

Similar, not cited

Close in wording, no citation either way

  1. 2025Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies
  2. 2026A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control
  3. 2022CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learning
  4. 2024Reinforcement Learning for Freeway Lane-Change Regulation via Connected Vehicles
  5. 2026CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control
  6. 2026VLALight: A Vision-Language-Action Model for Traffic Signal Control
  7. 2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
  8. 2025Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse