Hello World!

“Feedback is a method of controlling a system by reinserting into it the results of its past performance… if [this] is able to change the general method and pattern of performance, we have a process which may well be called learning.” — Norbert Weiner

About. Welcome. I’m a graduate researcher and Robotics M.S. student in the GRASP Lab at the University of Pennsylvania, advised by Professor George Pappas. I earned my B.S. in Mechanical Engineering from UCLA and will begin a Ph.D. in Fall 2026 to continue exploring autonomy in greater depth. This page is a living notebook for my work and ideas; over time, I’ll add short notes on topics I enjoy learning and how I’ve come to understand them.

Why Robotics. Nature seems to suggest that intelligence has less to do with what something is made of and more to do with whether it can close the loop between perception, computation, and action. Slime molds, for instance, can map out the absolute shortest path to their favorite food (oats!) using simple chemical gradients; ants turn incredibly minimal individual capabilities into colony-level intelligence through decentralized coordination; octopuses literally think with their arms, distributing most of their roughly 500 million neurons throughout eight limbs; and plants, lacking a nervous system entirely, make up roughly 80% of Earth’s biomass through slow, deliberate responses to their environment over evolutionary timescales.

To me, robotics is humanity’s most exciting attempt to build that same beautiful, closed-loop intelligence from the ground up. The word “robot” itself comes from Karel Čapek’s 1920 play R.U.R. (Rossum’s Universal Robots), via the Czech robota, meaning forced labor. It is always striking to me that a stage play about artificial workers has grown into a serious technical discipline spanning mathematics, physics, biology, philosophy, and even art. Fundamnetally, I’m drawn to building autonomous systems for two reasons: first, because it forces us to take our neat, abstract algorithms and ideas and throw them into the messy, unforgiving reality of the physical world; and second, because getting these intelligent systems right will gives us real leverage in tackling critical problems tied to human and planetary flourishing.

Technical Interests. I’m most interested in autonomy that combines learning and control for systems deployed on real hardware.

• Real-world RL: sample-efficient, uncertainty-aware methods that run on physical robots
• Planning and constrained optimization: MPC and trajectory optimization with learned models and policies
• Complex manipulation: contact-rich, long-horizon skills in unstructured environments
• Multi-agent autonomy: coordination and learning under partial, noisy, or conflicting information
• Safety and guarantees: robustness, generalization, and reliable behavior on critical tasks