Published works include 'End-to-end RL Improves Dexterous Grasping Policies', 'Visuomotor Policies to Grasp Anything with Dexterous Hands', and 'Synthetica: Large Scale Synthetic Data Generation for Robot Perception'.
Research Experience
Previously a researcher at NVIDIA working on robotics and simulation, collaborating with Ankur Handa, Nathan Ratliff, and Karl Van Wyk.
Education
Currently a PhD student at UC Berkeley, advised by Pieter Abbeel and Jitendra Malik; previously studied Engineering Science at the University of Toronto, collaborating with Prof. Florian Shkurti and Prof. Animesh Garg.
Background
My interests lie at the intersection of perception and control to build intelligent robot systems that can interact with the physical world. My current research focuses on leveraging learning-based methods to achieve human-like dexterous manipulation in unstructured environments.