Connected and Automated Vehicles

Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test

Jang, Kathy
Lichtle, Nathan
Vinitsky, Eugene
Shah, Adit
Bunting, Matthew
Nice, Matthew
Piccoli, Benedetto
Seibold, Benjamin
Work, Dan
Monache, Maria Laura Delle
Sprinkle, Jonathan M.
Lee, Jonathan
Bayen, Alexandre M.
2024

In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the...

Kernel-based Planning and Imitation Learning Control for Flow Smoothing in Mixed Autonomy Traffic

Fu, Zhe
Alanqary, Arwa
Kreidieh, Abdul Rahman
Bayen, Alexandre M.
2024

This article presents a new architecture for managing heterogeneous fleets aimed at achieving flow harmonization in mixed-autonomy traffic, demonstrating robustness across different sensing paradigms. We develop a kernel-based planning controller capable of providing anticipative coordination over low-bandwidth or high-latency networks. Furthermore, we employ a scenario-based optimization technique to tune the parameters of the proposed controller which offers performance improvement over the grid search technique across different simulation scenarios. Additionally, our architecture...

Traffic Smoothing Using Explicit Local Controllers: Experimental Evidence for Dissipating Stop-and-go Waves with a Single Automated Vehicle in Dense Traffic

Hayat, Amaury
Alanqary, Arwa
Bhadani, Rahul
Denaro, Christopher
Weightman, Ryan J.
Xiang, Shengquan
Lee, Jonathan W.
Bunting, Matthew
Gollakota, Anish
Nice, Matthew
Gloudemans, Derek A.
Zachár, Gergely
Davis, Jon F.
Delle Monache, Maria
Seibold, Benjamin
Bayen, Alexandre
Sprinkle, Jonathan M.
Work, Daniel B.
Piccoli, Benedetto
2025

This article presents experimental evidence of the ability of a single automated vehicle acting as a controller to effectively dissipate stop-and-go waves in real traffic. The automated vehicle succeeded in stabilizing the speed profile by reducing oscillations in time and speed variations between vehicles during rush hour on I-24 in the Nashville area. We detail the control design, deployment and results obtained in this experiment, conducted as part of the CIRCLES consortium’s “MegaVanderTest” 2022, which involved a total of 100 automated vehicles.

Reinforcement Learning-Based Oscillation Dampening: Scaling Up Single-Agent Reinforcement Learning Algorithms to a 100-Autonomous-Vehicle Highway Field Operational Test

Jang, Kathy
Lichtle, Nathan
Vinitsky, Eugene
Shah, Adit
Bunting, Matthew
Nice, Matthew
Piccoli, Benedetto
Seibold, Benjamin
Work, Daniel B.
Delle Monache, Maria
Sprinkle, Jonathan M.
Lee, Jonathan W.
Bayen, Alexandre M.
2025

In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the...

Traffic Control via Connected and Automated Vehicles (CAVs): An Open-Road Field Experiment with 100 CAVs

Lee, Jonathan W.
Wang, Han
Jang, Kathy
Lichtle, Nathan
Hayat, Amaury
Bunting, Matthew
Alanqary, Arwa
Barbour, William
Fu, Zhe
Gong, Xiaoqian
Gunter, George
Hornstein, Sharon
Kreidieh, Abdul Rahman
Nice, Mat-Thew W.
Richardson, William A.
Shah, Adit
Vinitsky, Eugene
Wu, Fangyu
Xiang, Shengquan
Almatrudi, Sulaiman
Althukair, Fahd
Bhadani, Rahul
Carpio, Joy
Chekroun, Raphael
Cheng, Eric
Chiri, Maria Teresa
Chou, Fang-Chieh
Delorenzo, Ryan
Gibson, Marsalis
Gloudemans, Derek A.
Gollakota, Anish
Ji, Junyi
Keimer, Alexander
Khoudari, Nour
Mahmood, Malaika
Mahmood, Mikail
Matin, Hossein Nick Zinat
McQuade, Sean T.
Ramadan, Rabie
Urieli, Daniel
Wang, Xia
Wang, Yanbing
Xu, Rita
Yao, Mengsha
You, Yiling
Zachár, Gergely
Zhao, Yibo
Ameli, Mostafa
Baig, Mirza Najamuddin
Bhaskaran, Sarah
Butts, Kenneth
Gowda, Manasi
Janssen, Caroline
Lee, John
Pedersen, Liam
Wagner, Riley
Zhang, Zimo
Zhou, Chang
Work, Daniel B.
Seibold, Benjamin
Sprinkle, Jonathan M.
Piccoli, Benedetto
Monache, Maria Laura Delle
Bayen, Alexandre M.
2025

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. Also called “phantom jams” or “stop-and-go waves,” 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...

Assessment of the Applicability of Cooperative Vehicle-Highway Automation Systems to Bus Transit and Intermodal Freight: Case Study Feasibility Analyses in the Metropolitan Chicago Region

Shladover, Steven E.
Miller, Mark A.
Yin, Yafeng
Balvanyos, Tunde
Bernheim, Lauren
Fishman, Stefanie R.
Amirouche, Farid
Mahmudi, Khurran T.
Gonzalez-Mohino, Pedro
Solomon, Joseph
Rawling, Gerald
Iris, Ariel
Bozic, Claire
2004

This report presents the results of its performance assessment of the feasibility of applying cooperative vehicle-highway automation systems (CVHAS) to bus transit and freight movements in the metropolitan Chicago area. Cooperative vehicle-highway automation systems are systems that provide driving control assistance or fully automated driving and are based on information about the vehicle's driving environment that can be received by communication from other vehicles or from the infrastructure, as well as from their own on-board sensors.

Experimental Verification of Discretely Variable Compression Braking Control for Heavy Duty Vehicles

Vahidi, Ardalan
Stefanopoulou, Anna G.
Farias, Phil
Tsao, Tsu Chin
2003

In this report a recursive least square scheme with multiple forgetting factors is proposed for on-line estimation of road grade and vehicle mass. The estimated mass and grade can be used to robustify many automatic controllers in conventional or automated heavy-duty vehicles. We demonstrate with measured test data from the July 26-27, 2002 test dates in San Diego, CA, that the proposed scheme estimates mass within 5% of its actual value and tracks grade with good accuracy. The experimental setup, signals, their source and their accuracy are discussed. Issues like lack of persistent...

A Fuzzy Rule-Based Controller For Automotive Vehicle Guidance

Hessburg, Thomas
Tomizuka, Masayoshi
1991

A fuzzy rule-based controller is applied to lateral guidance of a vehicle for an automated highway system. The fuzzy rules, based on human drivers' experiences, are developed to track the center of a lane in the presence of external disturbances and over a range of vehicle operating conditions.

Intelligent Vehicle/highway System Safety: Multiple Collisions In Automated Highway Systems

Hitchcock, Anthony
1995

In this report, a comparison is drawn between the casualty rates per failure on an automated highway system (AHS) according to the longitudinal control configuration used. The comparison is drawn between closed-spaced platooning, vehicle following of the types used in Autonomous Intelligent Cruise Control (AICC) and Cooperative Intelligent Cruise Control, and a point-following configuration (PFC). The model used permits evaluation of the consequences of a failure, allowing for the multiple collisions that usually ensue.

Longitudinal Control Development For IVHS Fully Automated And Semi - Automated System: Phase III

Hedrick, J. K.
Garg, V.
Gerdes, J. C.
Maciuca, D. B.
Swaroop, D.
1997

This report focuses on longitudinal issues regarding modeling and control of vehicles in an Intelligent Transportation Systems (ITS) setting. Specifically, the report addresses the issue of vehicle control in an automated highway system, brake actuation and brake control. Recent research findings in the area of automated vehicle platooning on isolated lanes of an automated highway are included. Performance specifications, control system architecture, vehicle control algorithms, actuator and sensor specifications and communication requirements are also discussed. The report also addresses...