Yewon Lee | University of Pennsylvania

About Me

I am a Ph.D. student in Computer and Information Science (CIS) at the GRASP Laboratory at the University of Pennsylvania, where I am advised by Prof. Rachel Holladay. My research interest centers around decision making, planning, and control for robot manipulation, particularly in contact-rich, long horizon settings.

I obtained my Master’s in Computer Science at the University of Toronto, where I was advised by Prof. Florian Shkurti and collaborated with Prof. Fabio Ramos. For my Master’s thesis, I developed a differentiable algorithm for task and motion planning that makes use of gradients from physics simulation. Prior to that, I completed my bachelor’s in Engineering Science at the University of Toronto. During this time, I interned at Epson’s Robotics R&D team researching computer vision algorithms for robotic manipulation.

I am gratefully supported by the NSERC Canada Graduate Scholarship - Doctoral, and have been honored to receive the Google DeepMind Fellowship, NSERC Canada Graduate Scholarship (Master’s), and Ontario Graduate Scholarship for my Master’s studies.

News

[September 2025] Awarded the NSERC Canada Graduate Scholarship for my PhD
[March 2025] Our work on differentiable task and motion planning (STAMP) has been accepted to RA-L 2025
[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] Awarded the Ontario Graduate Scholarship

Publications

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

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

IEEE Robotics and Automation Letters (RA-L), 2025.

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

Website arXiv Video Poster