@article{bibcite_36773,
  author = {Jonathan W Lee and Han Wang and Kathy Jang and Nathan Lichtl{\'e} and Amaury Hayat and Matthew Bunting and Arwa Alanqary and William Barbour and Zhe Fu and Xiaoqian Gong and George Gunter and Sharon Hornstein and Abdul Rahman Kreidieh and Mat-Thew W Nice and William A Richardson and Adit Shah and Eugene Vinitsky and Fangyu Wu and Shengquan Xiang and Sulaiman Almatrudi and Fahd Althukair and Rahul Bhadani and Joy Carpio and Raphael Chekroun and Eric Cheng and Maria Teresa Chiri and Fang-Chieh Chou and Ryan Delorenzo and Marsalis Gibson and Derek Gloudemans and Anish Gollakota and Junyi Ji and Alexander Keimer and Nour Khoudari and Malaika Mahmood and Mikail Mahmood and Hossein Nick Zinat Matin and Sean Mcquade and Rabie Ramadan and Daniel Urieli and Xia Wang and Yanbing Wang and Rita Xu and Mengsha Yao and Yiling You and Gergely Zach{\'a}r and Yibo Zhao and Mostafa Ameli and Mirza Najamuddin Baig and Sarah Bhaskaran and Kenneth Butts and Manasi Gowda and Caroline Janssen and John T Lee and Liam Pedersen and Riley Wagner and Zimo Zhang and Chang Zhou and Daniel B Work and Benjamin Seibold and Jonathan Sprinkle and Benedetto Piccoli and Maria Laura Delle Monache and Alexandre M Bayen},
  title = {Traffic Control via Connected and Automated Vehicles (CAVs): An Open-Road Field Experiment with 100 CAVs},
  abstract = {<p>The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. Also called {\textquotedblleft}phantom jams{\textquotedblright} or {\textquotedblleft}stop-and-go waves,{\textquotedblright} these instabilities are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system, referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment, the MegaVanderTest (MVT), leveraged a heterogeneous fleet of 100 longitudinally controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this article. The MegaController is a hierarchical control architecture that consists of two main layers. The upper layer is called the Speed Planner and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock onboard sensors. The Speed Planner ingests live data feeds provided by third parties as well as data from our own control vehicles and uses both to perform the speed assignment. The architecture of the Speed Planner allows for the modular use of standard control techniques, such as optimal control, model predictive control (MPC), kernel methods, and others. The architecture of the local controller allows for the flexible implementation of local controllers. Corresponding techniques include deep reinforcement learning (RL), MPC, and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers or only some. Likewise, control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars to electronic selection of adaptive cruise control (ACC) setpoints in others. The proposed architecture technically allows for the combination of all possible settings proposed previously, that is Speed Planner algorithms {\texttimes} local Vehicle Controller algorithms {\texttimes} full or partial sensing {\texttimes} torque or speed control. Most configurations were tested throughout the ramp up to the MegaVandertest (MVT).</p>},
  year = {2025},
  booktitle = {IEEE Control Systems},
  journal = {IEEE Control Systems},
  series = {IEEE Control Systems},
  volume = {45},
  pages = {28-60},
  month = {02/2025},
  institution = {Institute of Electrical and Electronics Engineers (IEEE)},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  issn = {1066-033X, 1941-000X},
  url = {https://doi.org/10.1109/mcs.2024.3498552},
  doi = {10.1109/mcs.2024.3498552},
}