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.

• 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.

Home page feature.

(Spotlight Talk)

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