I want to build machines that deeply understand both their own dynamics and their environment's, so they can act safely and efficiently in a world too complex to model by hand. In this setting, bigger models and more data are not enough. Reality keeps producing situations no dataset could anticipate. Continually learning from them requires a Real2Sim2Real loop, and my research develops each of its parts:
- Model: learn dynamics-grounded world models from real data.
- Act: plan and control safely in ways that are aligned with human intent (even when the models are wrong).
- Probe: let agents seek out what they don't yet know, through experiments, observation, or deployment, and use it to refit the model.
I've applied this loop to soft robots, spacecraft, and language-guided drone search, working at Stanford in Marco Pavone's Autonomous Systems Lab with the support of a Stanford Graduate Fellowship. Before that, I built lunar hardware at Caltech that won two NASA BIG Idea Challenge awards, and a tether management system for JPL's Axel cliff rover. Two of my papers have received Best Paper awards at AIAA SciTech, and a third was an IJRR Best Paper Honorable Mention. I also competed in the DARPA Subterranean Challenge with JPL's Team CoSTAR and was deputy lead on the first reasoning-model flight test at the USAF Test Pilot School.
Selected Publications
Full list ↗★ denotes equal contribution.
Selected Systems
NASA Visionary Concept Award
NASA Best Product Development Award
SciTech 2022 Best Paper
Experience
-
Autonomous Systems Lab, Stanford Stanford, CA
CurrentGraduate Research Assistant · Advisor: Prof. Marco Pavone
World models for real-time predictive control
-
USAF Test Pilot School Edwards AFB
2026Deputy Project Lead, Test Management (embedded from Stanford)
First reasoning-model-based ISR flight test; evaluation methodologies for foundation models in airborne operations
-
NASA Jet Propulsion Laboratory Pasadena, CA
Jun – Sep 2022Robotics System Engineering Intern · Mentors: Dr. Issa Nesnas & Dr. Travis Brown
Tether tension control and management system design for the Axel cliff rover
-
Aerospace Robotics and Control Lab, Caltech
2021 – 2022Research Fellow · Mentors: Prof. Soon-Jo Chung & Prof. Guanya Shi
Stochastic delay compensation for aggressive multirotor trajectory tracking
-
Honeywell Aerospace, Advanced Technology Group Tempe, AZ
Jun – Sep 2020Research and Development Intern
Learning-based real-time anomaly detection for metal additive manufacturing
-
TEAM CoSTAR JPL, MIT, Caltech, KAIST
2019 – 2020Research Fellow, DARPA Subterranean Challenge · Mentor: Prof. Joel W. Burdick
Autonomous hybrid flying/driving platform design and motion planning