CIRCLES

Using deep reinforcement learning and self-driving cars to improve traffic flow and reduce energy consumption

Learn More

What is CIRCLES?

Traffic jams and pollution? We help both with AI.

The Congestion Impacts Reduction via CAV-in-the-loop Lagrangian Energy Smoothing (CIRCLES) project aims to reduce instabilities in traffic flow, called "phantom jams," that cause congestion and wasted energy. If you have ever encountered a temporary traffic jam for no apparent reason, this might have been a phantom jam that occurred naturally because of human driving behavior.

Prior work on closed-course testing demonstrated that phantom jams can be reduced using autonomous vehicle technologies and specially-designed algorithms. The CIRCLES project seeks to extend this technology to real-world traffic, where reducing these negative traffic effects could provide ≥10% energy savings.

Preliminary vehicle and traffic flow detection in the I-24 Mobility Technology Interstate Observation Network (MOTION).
CIRCLES uses deep reinforcement learning to produce optimal traffic simulations. In this simulation, the autonomous vehicle learned to create a snake for optimal traffic flow.

Research Plan

Demonstrate traffic flow and energy savings in the real world.

The ambitious goals of the CIRCLES project will be achieved through a combination of computational development, vehicle technology deployment, and highway infrastructure construction. Novel research is being conducted in all of these areas by an interdisciplinary team across the United States.

Specific major research tasks include:
(1) Develop high-fidelity simulation tools that exhibit realistic traffic instabilities.
(2) Discover new techniques in multi-agent reinforcement learning.
(3) Develop control algorithms to transfer reinforcement learning policies to connected and autonomous vehicles.
(4) Develop, calibrate, and validate energy models for vehicles.
(5) Combine vehicle sensing, control, and communication technologies for traffic flow experiments.
(6) Build highway sensing infrastructure to measure traffic flow impacts by observing the position of every vehicle on the road.

Our Team

The CIRCLES Consortium consists of 5 lead researchers and 35 scholars coming from diverse academic backgrounds.

CIRCLES is led by UC Berkeley and the Institute of Transportation Studies (ITS) Berkeley, in coordination with Vanderbilt University, Temple University, Rutgers University-Camden, the Tennessee Department of Transportation, Toyota North America, and Nissan North America. The project is backed primarily by DOE and NSF funding. It will also provide the opportunity for engagement with major automotive partners and federal agencies (e.g., DOE, DOT).

Alexandre Bayen, ITS Director and Liao-Cho Professor, Department of Electrical Engineering & Computer Science, UC Berkeley

Maria Laura Delle Monache, Assistant Professor, Department of Civil & Environmental Engineering, UC Berkeley

Jonathan Lee, Senior Engineering Manager & Project Coordinator, Department of Electrical Engineering & Computer Science, UC Berkeley

Benedetto Piccoli, Vice Chancellor for Research and Joseph and Loretta Lopez Chair Professor, Department of Mathematical Sciences, Rutgers University-Camden

Benjamin Seibold, Professor, Department of Mathematics, Temple University

Jonathan Sprinkle, Professor, Department of Computer Science, Vanderbilt University

Daniel Work, Professor, Department of Civil and Environmental Engineering, Vanderbilt University

View the entire team

Products

FLOW

A deep reinforcement learning framework for mixed autonomy traffic.

Strym

A Python package for real-time logging, analysis and visualization of vehicle data from CAN bus.

I-24 MOTION

Interstate camera tracking for high-resolution vehicle trajectory data collection.

Libpanda

A software library and utilities for interfacing with vehicle hardware systems.

News

Card image cap
Nashville Tennesseean

Researchers say AI eased congestion on I-24

Card image cap
TechXplore

Massive traffic experiment pits machine learning against 'phantom' jams

Card image cap
PR Newswire

AI-powered cruise control system may pave the way to fuel efficiency and traffic relief

Card image cap
Vanderbilt News

AI-powered cruise control system may pave the way to fuel efficiency and traffic relief

Card image cap
WKRN News Channel 2 Nashville

Adaptive cruise control technology could ease phantom traffic jams, Vanderbilt study finds

Card image cap
Popular Science

An AI that lets cars communicate might reduce traffic jams

Card image cap
Fortune

You’re a worse driver than a robot: Research shows gaper blocks and looky-loos aren’t an issue with AI

Card image cap
The Associated Press

Researchers: AI in connected cars eased rush hour congestion

Card image cap
Berkeley News

Massive traffic experiment pits machine learning against ‘phantom’ jams

Card image cap
KTVU Channel 2 News Bay Area

UC Berkeley researchers test-drive new AI cars

Card image cap
Main Street Nashville

Traffic research project turns I-24 into driving lab

Card image cap
Good Word News

UC Berkeley researchers behind the world’s largest open-track traffic experiment

Card image cap
ABC 7 News

Bay Area researchers behind world's largest open-track traffic experiment

Card image cap
WSMV News Channel 4 Nashville

I-24 traffic experiment using technology to solve traffic jams

Card image cap
WABI News Channel 5 Maine

I-24 traffic experiment using technology to solve traffic jams

Card image cap
Fox 17 WZTV Nashville

World's largest traffic experiment being conducted in Nashville along I-24

Card image cap
WTVF News Channel 5 Nashville

'An MRI for traffic:' Open road testing now live on I-24

Card image cap
WKRN News Channel 2 Nashville

Traffic experiment to launch on I-24 in Nashville

Card image cap
Motor

World's largest open-track traffic experiment being conducted in Nashville Nov. 14-18

Card image cap
Tullahoma News

World's largest open-track traffic experiment being conducted in Nashville Nov. 14--18

Card image cap
PR Newswire

World's largest open-track traffic experiment being conducted in Nashville Nov. 14--18

Card image cap
TED Ed

Professor Seibold educates on phantom traffic jams

Card image cap
American Association for the Advancement of Science

UA Engineers Collaborate on $3.5M DOE Traffic-Flow Project

Card image cap
Built In

Machine Learning to Ease Traffic and Pollution Woes

Card image cap
Berkeley Institute of Transporation Studies

CIRCLES Project Kicks Off Multi-Campus Traffic Smoothing Study

Card image cap
CST @ Temple University

Temple Mathematician Part of $3.5M Project to Improve Traffic Flow and Fuel Savings

Card image cap
Berkeley Lab

Machine Learning to Help Optimize Traffic and Reduce Pollution

Collaborators