Biography
I am an nth-year PhD Student in the CILVR group advised by Lerrel Pinto. My interests include Robot and Reinforcement Learning to enable robots to sense, think, and act in unstructured environments.
I completed my undergraduate degree in Computer Science at the University of Washington, working at first in the Robotics and State Estimation Lab with Arunkumar Byravan on video prediction, then in the Movement Control Lab with Kendall Lowrey and Aravind Rajeswaran on off-policy reinforcement learning and nonlinear model predictive control.
- Robot Learning
- Reinforcement Learning
- Directed Exploration
-
PhD in Computer Science, 2020-present
New York University
-
BS/MS in Computer Science, 2015-2020
University of Washington
Featured Publications
Optimizing behaviors for dexterous manipulation has been a longstanding challenge in robotics, with a variety of methods from model-based control to model-free reinforcement learning having been previously explored in literature. Perhaps one of the most powerful techniques to learn complex manipulation strategies is imitation learning. However, collecting and learning from demonstrations in dexterous manipulation is quite challenging. The complex, high-dimensional action-space involved with multi-finger control often leads to poor sample efficiency of learning-based methods. In this work, we propose ‘Dexterous Imitation Made Easy’ (DIME) a new imitation learning framework for dexterous manipulation. DIME only requires a single RGB camera to observe a human operator and teleoperate our robotic hand. Once demonstrations are collected, DIME employs standard imitation learning methods to train dexterous manipulation policies. On both simulation and real robot benchmarks we demonstrate that DIME can be used to solve complex, in-hand manipulation tasks such as ‘flipping’, ‘spinning’, and ‘rotating’ objects with the Allegro hand. Our framework along with pre-collected demonstrations is publicly available at https://nyu-robot-learning.github.io/dime/