Computer Science & Mathematics · UT Austin
I’ll be applying to PhD programs this fall, for Fall 2027 admission.
I’m an undergrad at UT Austin studying Computer Science and Mathematics, where I’ve been lucky enough to be advised by Prof. Roberto Martín-Martín.
I care about robot learning in places where a mistake actually costs something. Most of our methods assume a forgiving environment, and a house is not one. That gets me interested in how robots perceive what’s around them, and in how they can pick up new skills by watching people without breaking the kitchen along the way. The question underneath all of it: can we really have robots that help out at home?
I’ve chased these questions in the Robot Interactive Intelligence (RobIn) lab, working on learning from human video, human-robot collaboration, and ways to tell whether a policy is actually safe. I also defended my undergraduate honors thesis, SafeManiBench, on benchmarking safety in robot manipulation.
TL;DR A unified, damage-aware simulation framework for household manipulation that makes physical safety measurable, enabling safer data collection, imitation learning, reinforcement learning, and VLA evaluation.
TL;DR A system for human-robot collaboration that uses mixed-initiative natural-language dialog so both agents can propose, accept, or reject who completes each step of a task, improving task success and user experience in physical robot trials.
TL;DR A benchmark for physics-grounded damage detection in manipulation, providing a unified mechanism for quantifying the safety of robot actions. Policies trained with damage-based safety metrics learn safer strategies with substantially lower risk.
TL;DR A framework that enables robots to safely and autonomously learn multi-step mobile manipulation tasks from a single human video by segmenting, translating, and adapting the demonstrated actions to their own morphology.