×

Chang Won (John) Lee

Hi there! I'm a 2nd-year PhD student at the University of Toronto, advised by Professor Steven Waslander in the Toronto Robotics and AI Lab. I am affiliated with University of Toronto Robotics Institute and Vector Institute. I obtained my Master's and Bachelor's degrees from the University of Toronto, with a Bachelor's in Engineering Science (Machine Intelligence major).

My research focuses on generalist robots that can follow open-ended instructions reliably in open-world settings. I am interested in task decomposition and reasoning, long-horizon embodied task planning, agent orchestration, generalist vision-language-action (VLA) policies, and learning from experience (continual and incremental learning). Previously, I worked on uncertainty quantification, multi-object tracking, and visual anomaly detection for autonomous driving and space robotics.

CV     Github     G. Scholar     LinkedIn    

Please don't hesitate to reach out if you have any questions or would like to chat!

john [dot] lee [at] robotics [dot] utias [dot] utoronto [dot] ca

UofT

PhD in Aerospace Engineering and Robotics
University of Toronto

September 2025 - Present
Advisor: Professor Steven Waslander

UofT

Master of Applied Science in Aerospace Engineering and Robotics
University of Toronto

September 2023 - September 2025
Advisor: Professor Steven Waslander

UofT

Bachelor of Applied Science in Engineering Science (Machine Intelligence)
University of Toronto

September 2018 - June 2023
Thesis Advisor: Professor Steven Waslander

DistillPlan: Distilling Episodes into Decomposition Schemas for Efficient Long-Horizon Embodied Task Planning

Chang Won Lee, M. Yuan, Steven L. Waslander
Under Review

FlowCLAS

FlowCLAS: Enhancing Normalizing Flow-Based Anomaly Segmentation Via Contrastive Learning

Chang Won Lee, Selina Leveugle, Paul Grouchy, Chris Langley, Svetlana Stolpner, Jonathan Kelly, Steven L. Waslander
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026
Webpage  •   Paper

ALLO

A Photorealistic Dataset and Vision-Based Algorithm for Anomaly Detection During Proximity Operations in Lunar Orbit

Selina Leveugle, Chang Won Lee, Svetlana Stolpner, Chris Langley, Paul Grouchy, Steven L. Waslander, Jonathan Kelly
IEEE Robotics and Automation Letters (RA-L), 2026
Paper  •   Code

UncertaintyTrack

UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking

Chang Won Lee, Steven L. Waslander
2024 IEEE International Conference on Robotics and Automation (ICRA)
Paper  •   Code

ProPanDL

ProPanDL: A Modular Architecture for Uncertainty-Aware Panoptic Segmentation

Jacob Deery, Chang Won Lee, Steven Waslander
2023 20th Conference on Robots and Vision (CRV)
Paper

Presentation of UncertaintyTrack at ICRA 2024

2026

Teaching Assistant for Robotics Capstone Design (ROB498)

2025

Teaching Assistant for Mathematics for Robotics (ROB310)

2025

Teaching Assistant for Artificial Intelligence (ROB311)

2024

Teaching Assistant for Introduction to Mobile Robotics (CSC477)

2024

Teaching Assistant for Mathematics for Robotics (ROB310)

2023

Teaching Assistant for Mathematics for Robotics (ROB310)

2022

Teaching Assistant for Linear Algebra for Engineering (MAT188)
aUtoronto

Software Engineer (General Member) at aUToronto (August 2021 - April 2023)

University of Toronto's self-driving car team.
Our team won all dynamic and static challenges at the SAE AutoDrive Challenge II in 2024.

2019 - 2022

University of Toronto Engineering Student Ambassador

2020 - 2021

University of Toronto Engineering Student Mentor