Postdoctoral Associate, CSAIL
Massachusetts Institute of Technology
Office: 32-380
Email: gchou [at] mit [dot] edu
CV   |    Scholar   |    ResearchGate


About me:

I was born and raised in Northern California. After earning dual B.S. degrees in Electrical Engineering and Computer Science and Mechanical Engineering from UC Berkeley in 2017, where I worked with Claire Tomlin and Anca Dragan, I left the eternal summer behind to receive an M.S. and Ph.D. in Electrical and Computer Engineering from the University of Michigan in 2019 and 2022, respectively. At Michigan, I was advised by Necmiye Ozay and Dmitry Berenson. Currently, I am a postdoc at MIT CSAIL, where I work with Russ Tedrake. I am a recipient of the National Defense Science and Engineering Graduate (NDSEG) fellowship and the NSF Graduate Research Fellowship, and was named a Robotics: Science and Systems (R:SS) Pioneer in 2022.

Research focus:

I design principled algorithms for efficient, data-driven robots that provide holistic, full-stack guarantees on safety and reliability in uncertain, human-centered environments. To achieve this, I leverage learned models for model-based control, and build and exploit knowledge of where these models can be trusted in order to enable robust behavior. Beyond machine learning and control theory, my algorithms also unify and build upon diverse tools in optimization, perception, statistics, human-robot interaction, planning, and formal methods. I also believe strongly in validating that the theoretical guarantees of my algorithms translate to the real world when deployed on hardware. These days, I am especially excited by applications in robotic manipulation and vision-based navigation. Please see this page for an overview of my research directions, and this page for a complete list of publications.

Safely Learning Task Specifications
from Humans

Reliable Planning and Control
with Learned Models

Fundamental Model-Based Tools
for Verifiable Control