3 research outputs found
The I-24 Trajectory Dataset
No full textThis dataset was created by recording CAN and GPS data from a single vehicle driving on I-24. The dataset includes values for Time, Velocity, Acceleration, Space Gap, Lateral Distance, Relative Velocity, Longitude GPS, Latitude GPS, Score, TrackID, L_Approach, R_Approach, L_Adjacent, and R_Adjacent. Data are preprocessed for your convenience into individual westbound or eastbound trajectories with mile markers and other relevant data fields added, in the labeled directories.
Nice, Matthew and Lichtle, Nathan and Gumm, Gracie and Roman, Michael and Vinitsky, Eugene and Elmadani, Safwan and Bunting, Matt and Bhadani, Rahul and Gunter, George and Kumar, Maya and McQuade, Sean and Denaro, Chris and Delorenzo, Ryan and Piccoli, Benedetto and Work, Dan and Bayen, Alex and Lee, Jonny and Sprinkle, Jonathan and Seibold, Benjami
Recommended from our members
Deep Reinforcement Learning for Autonomous Vehicle Traffic Control and Stabilization: From Simulation to a 100-Vehicle Highway Field Deployment
No full textHighway traffic instabilities, commonly manifested as stop-and-go waves or capacity drop at bottlenecks, represent a major source of energy waste and congestion in transportation systems. Even small fractions of autonomous vehicles (AVs) have the potential to dampen these phenomena and improve overall traffic flow. However, developing control methods that can transition from simulation to deployment in mixed-autonomy environments remains a fundamental challenge. The core problem lies in creating robust control algorithms that can handle the scale and complexity of multi-agent traffic interactions while maintaining safety and performance when deployed on actual roads with human drivers.This work establishes a complete research pipeline from simulation-based algorithm development to large-scale field validation of deep reinforcement learning (RL) methods for AV traffic control. The approach begins with developing multi-agent RL techniques for decentralized bottleneck control. It introduces Nocturne, a high-throughput driving simulator built on trajectory data to enable scalable multi-agent learning. Wave-smoothing cruise controllers are then trained directly on highway trajectory data, leading to a validated deployment pipeline that transfers learned policies to production vehicles without retuning. The methodology culminates in a large-scale field experiment where RL controllers developed in this work operate 100 connected and automated vehicles deployed in live rush hour traffic on the I-24 highway in Tennessee, achieving measurable traffic smoothing through distributed control. The work concludes by introducing neural network-based methods for traffic flow prediction via partial differential equations. Together, these contributions demonstrate both the feasibility and effectiveness of learning-based traffic control in mixed-autonomy environments, offering a clear path toward substantial improvements in highway energy efficiency and traffic congestion reduction
