AI-driven Eco-driving for Tackling Climate Change

Climate change is not a problem of the future. Greenhouse gas concentrations are at their highest levels in 2 million years. Global CO₂ emission levels are steadily increasing at a rapid pace making the Earth 1.1°C warmer than it was in the late 1800s. Records show that the last decade (2011-2020) was the warmest ever on Earth. Studies reveal that even global warming of 1°C (a point that has already been passed) could trigger climate tipping points. This could cause the climate system to become self-perpetuating leading to abrupt, irreversible, and dangerous impacts with serious implications for humanity.

Out of many sectors that directly contribute to climate change, the transportation sector in particular is responsible for the largest share of 29%, of which 77% is due to land transportation. Multiple efforts, therefore, have been taken to reduce transportation-related emission levels. The development of autonomous vehicles and the transformation of cities with modern technology have created a significant opportunity to enable roadways, driving patterns, and behaviors that are not just environmentally friendly but also safer and efficient.

Project Greenwave leverages deep reinforcement learning to inform transportation decarbonization by mitigating carbon intensity of urban driving. In Greenwave, we are building an ecosystem of tools, datasets, and methods for enabling roadway interventions and impact assessments of strategies to reduce carbon intensity of urban driving.

Our Core Goals

  • Development of new methodologies using machine learning, reinforcement learning, and modern control theory to reduce emission levels in transportation.
  • Conduct large-scale impact assessments of roadway intervention to inform climate-aware transition plans, public policies, and business models.
  • Design and develop data-driven emission models, driver behavior models, road network, and traffic datasets for enabling high-confidence impact assessments.
  • Development of metrics and data visualization tools as climate change research dissemination strategies for a diverse audience.
  • Experimental validation of roadway interventions and real-world deployment.


Learning Eco-Driving Strategies at Signalized Intersections
Vindula Jayawardana, Cathy Wu
European Control Conference (ECC), 2022
Press: On the road to cleaner, greener, and faster driving – MIT News

Home page feature.

Press: Perceptron: Risky teleoperation, Rocket League simulation and zoologist multiplication – Tech Crunch.
Podcast: The Loh Down on Science Podcast - NPR.
[Website] [Paper] [ICRA Presentation] [ICRA Poster] [ECC Video] [Cite]

The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning
Vindula Jayawardana, Catherine Tang, Sirui Li, Dajiang Suo, Cathy Wu
Advances in Neural Information Processing Systems (NeurIPS), 2022, To appear
[Website] [Paper] [Cite]

Eco-Lagrangian Control at Signalized Intersections
Vindula Jayawardana, Cathy Wu
Robotics for Climate Change Workshop at International Conference on Robotics and Automation (ICRA), 2022

(Spotlight Talk)

What is a Typical Signalized Intersection in a City? A Pipeline for Intersection Data Imputation from OpenStreetMap
Ao Qu*, Anirudh Valiveru*, Catherine Tang, Vindula Jayawardana, Baptiste Freydt, Cathy Wu
Transportation Research Board (TRB), 2022

Learning Surrogates for Diverse Emission Models
Edgar Ramirez Sanchez*, Catherine Tang*, Vindula Jayawardana, Cathy Wu
Tackling Climate Change with Machine Learning workshop, NeurIPS, 2022

Press Coverage

MIT News
Tech Crunch

Our Colloborators

Utah DOT

Our Team


Cathy Wu (Project Advisor)

Assistant Professor (MIT)


Vindula Jayawardana (Lead)

PhD Student (MIT)


Baptiste Freyd

Masters Student (ETH Zurich)

Utah DOT

Ao Qu

PhD Student (MIT)


Cameron Hickert

PhD Student (MIT)

Utah DOT

Sirui Li

PhD Student (MIT)


Catherine Tang

Undergraduate Student (MIT)

Utah DOT

Edgar Ramirez

Masters Student (MIT)


Sunera Avinash

Undergraduate Student

(University of Moratuwa)

Anirudh Veliveru

Undergraduate Student (MIT)


Jiaxin He

Undergraduate Student

(Vanderbilt University)

Zhongxia Yang

PhD Student (MIT)



Dajiang Suo

Research Scientist (MIT)

Contact Us
    For any questions or suggestions, please reach out to Professor Cathy Wu at cathywu [AT] mit [DOT] edu and Vindula Jayawardana (student lead) at vindula [AT] mit [DOT] edu.

Website Design
Last Updated on 09/24/2022