I’m an assistant professor at MIT in LIDS, CEE, & IDSS. I am passionate about policy-relevant research that pushes the boundaries of learning, control, and optimization.

My research group aims to advance the design of intelligent transportation systems. We develop models and methods that have implications for vision zero (safety), climate change mitigation (environment), and equity (cost). The predominant approach to advance roadways for the last two decades––autonomy––has yet to move the needle on sustainability, in terms of safety, cost, or environmental impact. Instead of relying solely on autonomy, we take a use-driven approach that considers roadway priorities and leverages technology to achieve them. Our work involves modeling multi-agent control problems for the complex coordination of roadway users and developing machine learning and control theoretic techniques to solve them. Overall, our work suggests that intelligently coordinating vehicles can make roadways safer and cleaner at a lower cost and faster than relying on autonomy alone. My goal is to lay foundations for practical solutions to long-standing challenges on roadways.

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 deep reinforcement learning to inform transportation decarbonization by mitigating carbon intensity of urban driving. (b) Human compatible driving considers the extent to which guided human drivers can achieve the same traffic-optimizing behavior of autonomous vehicles. (c) We are developing more robust learning-based methods for multi-agent control and coordination, motivated by the complexity of urban and warehouse systems. (d) We are developing learning-guided methods for discrete optimization, motivated by ever-evolving mobility systems and sustainable infrastructure. (d) We are developing statistical frameworks to inform “how safe is safe enough?” to deploy autonomous vehicles.

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 an introduction to opportunities to inform technology policy that excite me, 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 foundational methodologies we are developing, see Cities as Robots: Scalability, Operations, and Robustness from the RSS Workshop on Learning from Diverse, Offline Data in NYC (June 2022).

Teaching

Courses
1.041/1.200 Transportation. Spring 2023, Fall 2021, Fall 2020, Fall 2019.
6.7950 Reinforcement Learning. Fall 2022, Spring 2021, Spring 2020. Previously 6.246.
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 2022, Winter 2021
Advanced Reinforcement Learning: Summer 2022, Summer 2021

Group

I’m looking for postdoctoral researchers and PhD students!

Interested in a Masters/PhD? I’ll be considering students primarily via CEE, SES (IDSS), and EECS. I am also open to advising students with the right fit through MEng, Transportation, and TPP. If you are interested in working with me on impact-driven machine learning & control research for mobility, infrastructure, and sustainability, apply to any of these programs and list me in your application. A few special areas of interest include: deep (reinforcement) learning for combinatorial optimization, learning for control of multi-agent systems, and applied (reinforcement) learning for multi-agent mobility.

Interested in a postdoc? Please email me directly with [Postdoc starting 2023] in the title, and include a CV, short research statement, and 3 reference contacts. I’m particularly interested in hiring postdoctoral researchers with a strong background in machine learning, control, operations research, or public policy (!) who would like to expand their research to include high-impact applications in robotics warehouses, large-scale mobility systems, and/or wind farms (!).

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

Masters students
Edgar Ramirez Sanchez
Jason Teno (LGO)
Ao Qu (co-advised with Prof. Jinhua Zhao)

UROPs & Interns
Sunera Avinash (University of Moratuwa)
Jiaxin He (Vanderbilt)
Baptiste Freydt (ETH Zurich)
Kushal Chattopadhyay
Nrithya Renganathan
Kene Nnolim
Greg Pylypovych

Articles in review

[Non-terminal] Learning to Separate in Branch-and-Cut
Sirui Li*, Wenbin Ouyang*, Max Paulus, Cathy Wu

[Terminal] Transferability of Reinforcement Learning in Large and Parameterized Mixed Autonomy Systems
Zhongxia Yan, Cathy Wu

[Non-terminal] Decorrelating Neural Neighborhood Search for Multi-agent Path Finding
Zhongxia Yan, Cathy Wu

[Terminal] Integrated Analysis of Human-compatible Control for Traffic Flow Stability
Sirui Li, Roy Dong, Cathy Wu
( pre-print )

[Non-terminal] Mitigating The Braess’s Paradox in A Closed System Using Reinforcement Learning
Dingyi Zhuang*, Yuzhu Huang*, Vindula Jayawardana, Jinhua Zhao, Dajiang Suo, Cathy Wu
( pre-print )

[Terminal] Model-free Learning for Corridor Clearance in Mixed Autonomy
Dajiang Suo*, Vindula Jayawardana*, Cathy Wu

Terminal publications (top venues)

Cooperation for Scalable Supervision of Autonomy in Mixed Traffic
Cameron Hickert, Sirui Li, Cathy Wu
IEEE Transactions on Robotics (T-RO), 2023.
( paper / journal )

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.
( 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. Spotlight (<3%).
Also, International Conference on Machine Learning (ICML), 2021. Workshop on Subset Selection in Machine Learning.
( paper / website / OpenReview / poster / github )
Press: 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
Press: 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. Oral (2%).
Also, 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.
( paper / proceedings )
Press: 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.
( paper / proceedings )
Press: 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.
International Symposium on Transportation and Traffic Theory (ISTTT), 2015. Oral (14%).
( paper / journal / proceedings / github (system) / github (algorithm) )

Non-terminal publications

Stabilization Guarantees of Human-Compatible Control via Lyapunov Analysis
Sirui Li, Roy Dong, Cathy Wu
European Control Conference (ECC), 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, IEEE International Conference on Robotics and Automation (ICRA), 2022. Robotics for Climate Change Workshop. Invited flash talk.
( paper / website / poster )
Press: 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.
Transportation Research Board (TRB) Annual Meeting, 2015.
( paper / journal / proceedings )

Non-archival (preliminary work)

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.

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

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 )