Author: Michaela Jarvis | MIT Laboratory for Information and Decision Systems<\/p>\n
As far back as she can remember, Cathy Wu \u201912, MNG \u201913 wanted to find ways to solve problems to improve people\u2019s lives. Her parents were Taiwanese immigrants, and her father had a long commute to his job, which took him away from the family. On a tight budget, the rest of the family often stayed home on a street that was too busy for playing outdoors. Wu and her siblings ended up playing a lot of computer games.\u00a0<\/p>\n
Wu says her desire to make the world a better place, her dad\u2019s daily battle against traffic, and the games she played, like \u201cSimCity,\u201d were the seeds of her motivation to design safe, efficient transportation systems.\u00a0<\/p>\n
Wu is an associate professor in the MIT Department of Civil and Environmental Engineering (CEE) and the Institute for Data, Systems, and Society (IDSS), and a principal investigator in the Laboratory for Information and Decision Systems. Her research focuses on using machine learning and reinforcement learning (RL) to advance reliable strategies for improving a range of complex systems, including transportation.<\/p>\n
\u201cDesigning transportation systems consists of modeling and analyzing dozens, if not hundreds or thousands, of variants, which means that an evidence-driven approach to designing those systems is simply not within reach of today\u2019s tools,\u201d Wu says. \u201cThis is the role that RL plays. If successful, it would free transportation researchers and enable their practitioner partners to design the systems they want.\u201d<\/p>\n
Wu credits her older sister with instilling in her the desire to improve people\u2019s lives, and Wu\u2019s interest in transportation fits neatly into that ideal.<\/p>\n
\u201cI like transportation because it connects everyone. We all use it, we all experience it, we all have issues with it. So, at some level, we\u2019re all interested in the system being better,\u201d she says.<\/p>\n
Wu got interested in applying artificial intelligence to transportation while earning her undergraduate degree at MIT, after attending a lecture on autonomous vehicles by the late professor Seth Teller. The lecture, which Teller gave during an Independent Activities Period robotics competition (that Wu actually won), was the event that honed her particular approach to transportation research, Wu says. She began working with Teller, and when he stopped concentrating on autonomous vehicles, he encouraged Wu to transfer to Professor Daniela Rus, who had done research on robotaxis.<\/p>\n
\u201cI\u2019m very grateful to the people who helped me explore those interests and helped me become the person I am now,\u201d she says, specifically naming Teller, Rus, and \u201cmy friends at Dropbox,\u201d who invited her to do a second internship focused on transportation issues.<\/p>\n
After her master\u2019s degree at MIT, Wu went on to earn her PhD at the University of California at Berkeley. During that time, she observed that transportation researchers were spending years developing optimization methods to model and analyze a single new variant of a system. Her approach as a computer scientist working to develop RL and optimization methodologies to address transportation challenges held the promise of exponentially improved efficiency.<\/p>\n
In 2018, Wu\u2019s last year of her PhD at UC Berkeley, she successfully applied RL to a traffic problem: automatically analyzing the potential traffic flow impact of autonomous vehicles in a range of different traffic networks. The research went viral.<\/p>\n
While this could have been a \u201cthe rest is history\u201d moment for Wu, RL turned out to be a flighty friend. Wu worked on RL theory in a postdoc at Microsoft and came back to MIT as faculty drawn, she says, by the sustainability focus of CEE, and IDSS\u2019s emphasis on infusing data science into other disciplines.<\/p>\n
Yet over the next two years, Wu\u2019s further attempts to apply RL to traffic problems failed.<\/p>\n
\u201cThat was stressful,\u201d Wu says, \u201cit was unclear whether the problem was me (the advisor), my students, the traffic domain, or RL itself.\u201d<\/p>\n
Still, the earlier research was a proof-of-concept demonstration that RL could be applied to transportation systems.<\/p>\n
And in 2022, she and her students identified that RL algorithms are so sensitive that an algorithm that works on one problem may not on even a closely related one. A key result, which Wu says she is proudest of \u201cbecause it was like the light at the end of a long tunnel of negative results,\u201d came in 2023. She and her team of researchers devised a way to work around the sensitivity of RL. The team found that while RL may not train well on 90 percent of a group of problems, it can train quite well on 10 percent. And by training RL models on those problems that solve and generalize well, the resultant models collectively perform well on a set of related problems, even those that would not have been solved through direct training. The researchers designed an algorithm to determine which problems to use RL to train, and that algorithm improved training efficiency by up to 30 times, meaning that what would normally have required 100 training models may only require three models.<\/p>\n
\u201cThis work gave me back the confidence that reinforcement learning can play an important role in solving hard optimization problems, including in transportation,\u201d Wu says. \u201cNow, a good chunk of my group works on the topic of contextual RL, which is the setting where RL seeks to solve a space of related problems.\u201d<\/p>\n
Wu\u2019s more recent research applies RL to solve a hard transportation optimization problem with important policy implications: the work shows that eco-driving measures in which vehicle speeds are intelligently controlled to reduce excessive stopping and starting could reduce vehicle emissions by between 11 and 22 percent. The system provides evidence that policies instituting such measures could significantly improve system efficiency, and is \u201ca demonstration that RL can be used to inform transportation policy on problems of practical importance,\u201d Wu says.<\/p>\n
\u201cI am a big fan of evidence-based policy and believe it\u2019s the basis for a thriving democratic society, yet our societal systems are so complex,\u201d Wu says. \u201cPeople can bicker forever about what\u2019s better or worse, but I do believe that there are questions we bicker about that can be analyzed systematically using data and have objective answers. A large part of the reason I am in academia is to better understand how technology can support democratic societal decision-making.\u201d<\/p>\n
Wu says that much of the work she and her team have done over the last several years has produced algorithms \u201cto streamline the development of solvers for hard optimization problems, whether they are related to transportation or to other systems, such as logistics, supply chains, manufacturing, and resource allocation.<\/p>\n
\u201cThis alludes to my preferred style of work,\u201d Wu says, \u201cwhich is called use-inspired basic research,\u201d explaining that such research addresses a practical problem, developing fundamental knowledge that often translates to other practical problems. Her students start by probing consequential problems ranging from safety to congestion to accessibility, identifying where existing methods fall short, and allowing the problems themselves to shape the direction of the research.<\/p>\n
At the same time, Wu\u2019s desire to help others on a more personal level plays out in her teaching.<\/p>\n
\u201cI love working with students, both in the classroom and research mentoring,\u201d she says. \u201cIt makes my day when I am able to teach someone something \u2014 when I see that light bulb go on in a student.\u201d<\/p>\n
In addition to earning academic honors, including a 2023 National Science Foundation Faculty Early Career Development Award, Wu has also been formally celebrated for her teaching and mentoring, including with the Ole Madsen Mentoring Award in 2025.<\/p>\n
What does she tell students confronting extremely complicated problems?<\/p>\n
\u201cBe patient. Start small. Societal impact is a lifelong endeavor, not something to be accomplished in a few years,\u201d Wu says. \u201cIt will take years to really understand what\u2019s going on and where the real problems are. In the meantime, try to be helpful. Be curious. Ask many questions.\u201d<\/p>\n<\/div>\n
Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"