I’m an assistant professor at MIT in LIDS, CEE, & IDSS.
I am a technologist, but I believe it is just as important to understand the impact of the technologies, as it is to build them. That’s why I aim to understand how beneficial autonomous mobility systems are for society. I study the impact of autonomous and semi-autonomous vehicles, including on congestion, climate change, safety, and equity. I leverage machine learning and control theory in three interconnected research directions: 1) developing generalizable learning-based methods for multi-agent coordination, 2) modeling the dynamics and interactions of autonomous mobility systems with humans, and 3) assessing the societal impact of autonomous mobility systems using data-informed simulations. My research advances robotics, machine learning, and transportation by providing methods, tools, and insights for designing and evaluating socially beneficial and sustainable autonomous mobility solutions.
I previously completed a postdoc with the Microsoft Research Reinforcement Learning group and my PhD in EECS at UC Berkeley. I received a BS and MEng in EECS at MIT. I have also spent time at OpenAI, Waymo, Dropbox, Facebook, and several startups.
Current project highlights: (a) Project Greenwave leverages reinforcement learning to inform transportation decarbonization by mitigating carbon intensity of urban driving. (b) Advisory autonomy designs real-time driving advisories for human drivers to achieve the same traffic-optimizing behavior of autonomous vehicles. (c) Multi-agent autonomous driving provides methods for multi-agent control and coordination that are versatile, generalizable, and efficient. Applications include (semi-)autonomous vehicles and warehouse automation. (d) Learning-guided methods for discrete optimization achieves the best of both worlds from machine learning and optimization, to better cope with increasing complexity in real-world optimization. Applications include vehicle routing problems (VRP) and mixed integer linear programming (MILP). (e) Systems safety for autonomous mobility coordinates physical assets, such as through remote supervision, to provide system-level safety assurances.
Research awards: I am the recipient of a NSF Career Award aimed at advancing learning for generalization in large-scale cyber-physical systems. We are also grateful for active support from Amazon, National Science Foundation (NSF), Mathworks, MIT Mobility Initiative (MMI), MIT Energy Initiative (MITEI), Microsoft Research, Utah Department of Transportation (UDOT), and MIT Research Support Committee.
News | Teaching | Group | Publications
News
For a gentle introduction to how I think about advancing sociotechnical systems, see The Hidden Cause of Traffic Jams—and How to Solve Them (NOVA, 2022) and How Cities Can Reshape Cars (TEDxMIT, 2021).
For a recent research talk that goes into the engineering science and foundational methodologies we are developing, see Intelligent Coordination for Sustainable Roadways (ETH Autonomy Talks, May 2023).
- May 2023: Our T-RO 2023 article on increasing safety and reliability of autonomous vehicles was featured on MIT News! We analyzed how cooperative intelligence and ideas from air traffic control can drastically improve reliability of autonomous vehicles.
- Mar 2023: Thrilled to be awarded an NSF CAREER Award to study generalization for advancing large-scale cyber-physical systems.
- Aug 2022: It was fun to geek out about the Hidden Cause of Traffic Jams—and How to Solve Them for this fantastic educational video by NOVA.
- May 2022: Thrilled for our ECC 2022 work on employing artificial intelligence to help autonomous vehicles avoid idling at red lights to be featured on the MIT front page.
- February 2022: I had a fantastic conversation about the future of our roads (hint hint: powered by AI) on The Robot Brains podcast by Professor Pieter Abbeel.
- December 2021: I had a fun interview with the MIT Schwarzman College of Computing on our new project with Amazon, where we’ll be tackling algorithmic challenges of coordinating hundreds of robots — with the ultimate goal of safely integrating automation and AI into our world.
- December 2021: Our NeurIPS 2021 Spotlight Talk on machine learning for speeding up vehicle routing was featured by MIT News! We devise a strategy which accelerates the best algorithmic solvers by 10-100x for large sets of cities.
- January 2020: I was immensely honored to testify on the future of AI in transportation to the National Academy’s Transportation Research Board (TRB) at the Executive Committee Policy Session on Artificial Intelligence in Transportation.
(For more, see: earlier news.)
Teaching
Courses
6.7920 Reinforcement Learning. Fall 2023, Fall 2022, Spring 2021, Spring 2020. (Previously 6.7950/6.246.)
1.041/1.200 Transportation. Spring 2023, Fall 2021, Fall 2020, Fall 2019.
6.231 Dynamic Programming and Reinforcement Learning. Spring 2022.
EE290O Multi-agent reinforcement learning for autonomous traffic. Fall 2018.
Outreach and Professional Education
These courses are intended for industry professionals and not MIT students.
Reinforcement Learning: Summer 2023, Summer 2022, Winter 2021
Advanced Reinforcement Learning: Summer 2023, Summer 2022, Summer 2021
Group
I’m looking for postdoctoral researchers and PhD students!
Interested in a PhD? I’ll be considering students primarily via CEE, SES (IDSS), and EECS. I am also open to advising students with the right fit from other programs. If you are interested in working with me on impact-driven machine learning & control research for (semi-)autonomous mobility, apply to any of these programs and list me in your application. A few special areas of interest include: mixed autonomy traffic, learning-based control and coordination of multi-agent systems, machine learning for discrete optimization, modeling infrastructure for enabling autonomous mobility, environmental sustainability, and road safety.
Interested in a postdoc? Please email me directly with [Postdoc starting 2024] in the title, and include a CV, short research statement, and 3 reference contacts. I’m particularly interested in candidates with a strong background in machine learning, control, or operations research who would like to expand their research to include high-impact applications in (semi-)autonomous mobility.
I greatly value diversity and inclusion in STEM through teaching, mentorship, and outreach. We are a highly collaborative and welcoming lab with diverse backgrounds that come together to make the whole stronger than the sum of its parts. I strongly believe that diversity in perspective is necessary to solve the world’s most challenging problems.
PhD students
Zhongxia “Zee” Yan
Vindula Jayawardana
Sirui Li
Cameron Hickert
Wenbin Ouyang
Jung Hoon Cho
Han Zheng
Shreyaa Raghavan
Masters students
Edgar Ramirez Sanchez
Ao Qu (co-advised with Prof. Jinhua Zhao)
Jessica Ding
UROPs & Interns
Sunera Avinash (University of Moratuwa)
Jiaxin He (Vanderbilt)
Baptiste Freydt (ETH Zurich)
Kushal Chattopadhyay
Nrithya Renganathan
Ram Goel
Tianyue Zhou
Karmen Lu
Articles in review
Multi-agent Path Finding for Cooperative Autonomous Driving
Zhongxia Yan, Han Zheng, Cathy Wu
Generalizing Eco-Lagrangian Control via Multi-residual Task Learning
Vindula Jayawardana, Sirui Li, Cathy Wu, Yashar Farid, and Kentaro Oguchi
Learning Surrogates for Diverse Vehicle Emission Models
Edgar Ramirez Sanchez, et al.
Decorrelating Neural Neighborhood Search for Multi-agent Path Finding
Zhongxia Yan, Cathy Wu
Feature Selection for Policy Learning via Mutual Information
Juan Jose Garau Luis, Edward Crawley, Cathy Wu.
Transferability of Reinforcement Learning in Large and Parameterized Mixed Autonomy Systems
Zhongxia Yan, Cathy Wu
Model-free Learning for Corridor Clearance in Mixed Autonomy
Dajiang Suo*, Vindula Jayawardana*, Cathy Wu
Journal & selective conference publications
Learning to Configure Separators in Branch-and-Cut
Sirui Li*, Wenbin Ouyang*, Max B. Paulus, Cathy Wu
Advances in Neural Information Processing Systems (NeurIPS), 2023. [26% acceptance rate]
Integrated Analysis of Coarse-grained Control for Traffic Flow Stability
Sirui Li, Roy Dong, Cathy Wu
IEEE Transactions on Control of Network Systems (T-CNS), 2023. To appear.
( pre-print )
Cooperation for Scalable Supervision of Autonomy in Mixed Traffic
Cameron Hickert, Sirui Li, Cathy Wu
IEEE Transactions on Robotics (T-RO), 2023.
( paper / journal )
Media: Exploring new methods for increasing safety and reliability of autonomous vehicles – MIT News
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. [26% acceptance rate]
( paper / website / OpenReview / video / slides / poster )
Unified Automatic Control of Vehicular Systems with Reinforcement Learning
Zhongxia Yan, Abdul R. Kreidieh, Eugene Vinitsky, Alexandre M. Bayen, Cathy Wu
IEEE Transactions on Automation Science and Engineering (T-ASE), 2022.
Additionally selected for presentation at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
( paper / journal / website / github )
Interview: On the Future of Our Roads – The Robot Brains Podcast
Learning to Delegate for Large-scale Vehicle Routing
Sirui Li*, Zhongxia Yan*, Cathy Wu
Advances in Neural Information Processing Systems (NeurIPS), 2021. [26% acceptance rate] Spotlight (<3%).
Also presented at International Conference on Machine Learning (ICML), 2021. Workshop on Subset Selection in Machine Learning.
( paper / website / OpenReview / poster / github )
Media: Machine learning speeds up vehicle routing – MIT News
Flow: A Modular Learning Framework for Mixed Autonomy Traffic
Cathy Wu, Aboudy Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre M. Bayen
IEEE Transactions on Robotics (T-RO), 2021.
( paper / journal / videos / website / github )
Interview: Simulating the Future of Traffic with RL w/ Cathy Wu – TWIML AI Podcast
Interview: The Future of Mixed-Autonomy Traffic with Alexandre Bayen – TWIML AI Podcast
Media: Science, Wired, O’Reilly (Chinese version), Berkeley College of Engineering, abc News, Berkeley Lab, India Times, and Russian Forbes
Block simplex signal recovery: a method comparison and an application to routing
Cathy Wu, Alexei Pozdnoukhov, Alexandre M. Bayen
IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2019.
( journal / github )
Variance Reduction for Policy Gradient Using Action-Dependent Factorized Baselines
Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M Bayen, Sham Kakade, Igor Mordatch, Pieter Abbeel
International Conference on Learning Representations (ICLR), 2018. [25% acceptance rate] Oral (2%).
Also presented at Conference on Neural Information Processing Systems (NeurIPS), 2017. Deep Reinforcement Learning Symposium. Contributed talk.
( paper / OpenReview )
Benchmarks for reinforcement learning in mixed-autonomy traffic
Eugene Vinitsky*, Aboudy Kreidieh*, Luc Le Flem, Nishant Kheterpal, Kathy Jang, Cathy Wu, Fangyu Wu, Richard Liaw, Eric Liang, Alexandre M. Bayen.
Conference on Robot Learning (CoRL), 2018. [31% acceptance rate]
( paper / proceedings )
Media: Watch just a few self-driving cars stop traffic jams – Science
Emergent behaviors in mixed-autonomy traffic
Cathy Wu, Aboudy Kreidieh, Eugene Vinitsky, Alexandre M. Bayen
Conference on Robot Learning (CoRL), 2017. [29% acceptance rate]
( paper / proceedings )
Media: Autonomous Vehicles: The Answer to Our Growing Traffic Woes – Wired
Cellpath: fusion of cellular and traffic sensor data for route flow estimation via convex optimization
Cathy Wu, Jerome Thai, Steve Yadlowsky, Alexei Pozdnoukhov, Alexandre M. Bayen
Transportation Research: Part C, 2015.
Additionally selected for presentation at the International Symposium on Transportation and Traffic Theory (ISTTT), 2015. [25% acceptance rate] Oral (14%).
( paper / journal / proceedings / github (system) / github (algorithm) )
Additional conference publications
Multi-Behavior Learning For Socially Compatible Autonomous Driving
S. Jayawardana, V. Jayawardana, K. Vidanage, C. Wu.
IEEE Intelligent Transportation Systems Conference (ITSC), 2023.
PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Autonomy
A. Hasan, N. Chakraborty*, H. Chen*, J. Cho, C. Wu, and K. Driggs-Campbell
IEEE Intelligent Transportation Systems Conference (ITSC), 2023.
( pre-print )
Stabilization Guarantees of Human-Compatible Control via Lyapunov Analysis
Sirui Li, Roy Dong, Cathy Wu
European Control Conference (ECC), 2023.
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) Annual Meeting, 2023.
The Braess Paradox in Dynamic Traffic
Dingyi Zhuang*, Yuzhu Huang*, Vindula Jayawardana, Jinhua Zhao, Dajiang Suo, Cathy Wu
IEEE Intelligent Transportation Systems Conference (ITSC), 2022.
( paper / proceedings )
Learning Eco-Driving Strategies at Signalized Intersections
Vindula Jayawardana, Cathy Wu
European Control Conference (ECC), 2022.
Also presented at IEEE International Conference on Robotics and Automation (ICRA), 2022. Robotics for Climate Change Workshop. Invited flash talk.
( paper / website / poster )
Media: On the road to cleaner, greener, and faster driving – MIT News. Home page feature.
Piecewise Constant Policies for Human-Compatible Congestion Mitigation
Mayuri Sridhar, Cathy Wu
IEEE Intelligent Transportation Systems Conference (ITSC), 2021.
( proceedings )
Reinforcement Learning for Mixed Autonomy Intersections
Zhongxia Yan, Cathy Wu
IEEE Intelligent Transportation Systems Conference (ITSC), 2021.
( paper / proceedings / github )
Mixed Autonomous Supervision in Traffic Signal Control
Vindula Jayawardana, Anna Landler, Cathy Wu
IEEE Intelligent Transportation Systems Conference (ITSC), 2021.
( proceedings )
Stabilizing traffic with autonomous vehicles
Cathy Wu, Alexandre M. Bayen, Ankur Mehta
International Conference on Robotics and Automation (ICRA), 2018.
( proceedings / talk video )
Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion
Eugene Vinitsky, Kanaad Parvate, Abdul R. Kreidieh, Cathy Wu, Alexandre M. Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2018.
( paper / proceedings )
Dissipating stop-and-go waves in closed and open networks via deep reinforcement learning
Aboudy Kreidieh, Cathy Wu, Alexandre M. Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2018.
( paper / proceedings )
Multi-lane Reduction: A Stochastic Single-lane Model for Lane Changing
Cathy Wu, Eugene Vinitsky, Abdul R. Kreidieh, Alexandre M. Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2017.
( proceedings )
Framework for Control and Deep Reinforcement Learning in Traffic
Cathy Wu, Kanaad Parvate, Nishant Kheterpal, Leah Dickstein, Ankur Mehta, Eugene Vinitsky, Alexandre M. Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2017.
( proceedings )
Clustering for Set Partitioning with a Case Study in Ridesharing
Cathy Wu, Ece Kamar, Eric Horvitz
IEEE Intelligent Transportation Systems Conference (ITSC), 2016. Best paper award.
( paper / proceedings )
Optimizing the diamond lane: A more tractable carpool problem and algorithms
Cathy Wu, K. Shankari, Ece Kamar, Randy Katz, David Culler, Christos Papadimitriou, Eric Horvitz, Alexandre M. Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2016.
( paper / proceedings )
Convex programming on the l1-ball and on the simplex via isotonic regression
Jerome Thai, Cathy Wu, Alexei Pozdnoukhov, Alexandre M. Bayen
Conference on Decision and Control (CDC), 2015.
( paper / proceedings )
Link Density Inference from Cellular Infrastructure
Steve Yadlowsky, Jerome Thai, Cathy Wu, Alexei Pozdnoukhov, Alexandre M. Bayen
Transportation Research Record (TRR), 2015.
Additionally selected for presentation at the Transportation Research Board (TRB) Annual Meeting, 2015.
( paper / journal / proceedings )
Abstracts and workshop papers
Learning Surrogates for Diverse Emission Models
Edgar Sanchez*, Catherine Tang*, Vindula Jayawardana, Cathy Wu
Advances in Neural Information Processing Systems (NeurIPS), 2022. Workshop on Tackling Climate Change with Machine Learning.
( paper / slides / talk )
Reinforcement Learning for Empirical Supervision Scaling of Autonomous Vehicles
Cameron Hickert, Cathy Wu.
IEEE International Conference on Robotics and Automation (ICRA), 2022. Workshop Safe and Reliable Autonomy Under Uncertainty.
Sociotechnical Specification for the Broader Impacts of Autonomous Vehicles
Thomas Krendl Gilbert, Aaron Snoswell, Michael Dennis, Rowan McAllister, Cathy Wu
IEEE International Conference on Robotics and Automation (ICRA), 2022. Fresh Perspectives on Autonomous Driving Workshop.
( paper )
Learning to Dissipate Traffic Jams with Piecewise Constant Control
Mayuri Sridhar, Cathy Wu
Conference on Neural Information Processing Systems (NeurIPS), 2021. Workshop on Tackling Climate Change with Machine Learning.
( paper / slides / talk / proceedings )
Theses
Learning and Optimization for Mixed Autonomy Systems – A Mobility Context
Cathy Wu
Thesis. PhD, Electrical Engineering and Computer Sciences, UC Berkeley, 2018.
( thesis / summary )
Award: First Place 2019 IEEE ITSS Best Ph.D. Dissertation Award (news)
Award: 2018 Milton Pikarsky Memorial Award from the Council of University Transportation Centers (CUTC) for the best Doctoral dissertation in the field of science and technology in transportation studies (news).
Selected other writing
Steering Innovation for Autonomous Vehicles towards Societally Beneficial Outcomes
Thomas Krendl Gilbert, Cathy Wu, and Michael Dennis
Day One Project, Federation of American Scientists. June 2021.
( policy memo / summary )
It’s Time to Do Something: Mitigating the Negative Impacts of Computing Through a Change to the Peer Review Process
Brent Hecht, Lauren Wilcox, Jeffrey P. Bigham, Johannes Schöning, Ehsan Hoque, Jason Ernst, Yonatan Bisk, Luigi De Russis, Lana Yarosh, Bushra Anjum, Danish Contractor, Cathy Wu
ACM Future of Computing Academy Blog, 2018.
( article )
Traffic Jammin’: Making automated transportation a reality
Cathy Wu
Berkeley Science Review, 2016.
( article )
Automating us: The entanglement of people and machines
Daniel Aranki*, Roel Dobbe*, Jaime F. Fisac*, Cathy Wu*
Berkeley Science Review, 2015.
( article )
How to Lead a Technical Reading Group
Cathy Wu, Oct 2012.
( paper )