mlsanityData to 7 Oct 2026

Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory Data

arXiv 2401.09666 ↗First posted 18 Jan 2024eess.SY cs.AI cs.MAcited by 0

On the map: End-to-end autonomous driving → Cooperative and V2X driving

Abstract (arXiv)

Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel efficiency in mixed autonomy traffic. We bypass the common issue of having to carefully fine-tune a large traffic microsimulator by leveraging real-world trajectory data from the I-24 highway in Tennessee, replayed in a one-lane simulation. Using standard deep reinforcement learning methods, we train energy-reducing wave-smoothing policies. As an input to the agent, we observe the speed and distance of only the vehicle in front, which are local states readily available on most recent vehicles, as well as non-local observations about the downstream state of the traffic. We show that at a low 4% autonomous vehicle penetration rate, we achieve significant fuel savings of over 15% on trajectories exhibiting many stop-and-go waves. Finally, we analyze the smoothing effect of the controllers and demonstrate robustness to adding lane-changing into the simulation as well as the removal of downstream information.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving. Builds on 6 of its 21 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

6 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Cooperative Driving for Speed Harmonization in Mixed-Traffic Environments15 Feb

Other references · 5

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  3. 2017Dissipation of stop-and-go waves via control of autonomous vehicles: Field experimentscited by 41
  4. 2018Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehiclescited by 14
  5. 2021Integrated Framework of Vehicle Dynamics, Instabilities, Energy Models, and Sparse Flow Smoothing Controllerscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Traffic Shaping and Hysteresis Mitigation Using Deep Reinforcement Learning in a Connected Driving Environment
  2. 2021Scalable Multiagent Driving Policies For Reducing Traffic Congestion
  3. 2019Driving in Dense Traffic with Model-Free Reinforcement Learning
  4. 2024Multi-Task Lane-Free Driving Strategy for Connected and Automated Vehicles: A Multi-Agent Deep Reinforcement Learning Approach
  5. 2025A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator
  6. 2021Learning a Robust Multiagent Driving Policy for Traffic Congestion Reduction
  7. 2024Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization
  8. 2024Roadside Units Assisted Localized Automated Vehicle Maneuvering: An Offline Reinforcement Learning Approach