TY - GEN
T1 - Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data
AU - Lichtle, Nathan
AU - Vinitsky, Eugene
AU - Nice, Matthew
AU - Seibold, Benjamin
AU - Work, Dan
AU - Bayen, Alexandre M.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I-24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.
AB - Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I-24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.
UR - http://www.scopus.com/inward/record.url?scp=85134317127&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134317127&partnerID=8YFLogxK
U2 - 10.1109/ICRA46639.2022.9811912
DO - 10.1109/ICRA46639.2022.9811912
M3 - Conference contribution
AN - SCOPUS:85134317127
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 2884
EP - 2890
BT - 2022 IEEE International Conference on Robotics and Automation, ICRA 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 39th IEEE International Conference on Robotics and Automation, ICRA 2022
Y2 - 23 May 2022 through 27 May 2022
ER -