Yewon Lee | University of Toronto

About Me

I am a second year research-stream M.Sc. student in Computer Science at the University of Toronto, supervised by Florian Shkurti at the Robot Vision and Learning Lab (RVL). I am interested in task and motion planning (TAMP) for robotics, grapsing, robot learning, and differentiable physics simulators. For my M.Sc. thesis, I am working on developing a differentiable TAMP algorithm using probabilistic inference and differentiable physics. My work is gratefully funded by the Google DeepMind Fellowship, NSERC Canada Graduate Scholarship (Master’s), and Ontario Graduate Scholarship.

Prior to starting my M.Sc., I completed my B.A.Sc. in Engineering Science from the University of Toronto with a major in Aerospace Engineering and double minors in Robotics and AI. During this time, I also interned at Epson’s robotics R&D team where I worked on computer vision algorithms.

News

[October 2023] My workshop paper on Differentiable TAMP was accepted to the LEAP Workshop at CoRL 2023!
[July 2023] Selected to attend Robotics: Science and Systems 2023 as an Inclusion Fellow
[July 2023] Received the Ontario Graduate Scholarship

Publications

STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent

Yewon Lee, Philip Huang, Krishna Murthy Jatavallabhula, Andrew Z. Li, Fabian Damken, Eric Heiden, Kevin Smith, Derek Nowrouzezahrai, Fabio Ramos, Florian Shkurti

Conference on Robot Learning (CoRL), Learning Effective Abstractions for Planning Workshop, 2023.

PDF Poster