My research interest lies at the intersection of robotics, computer vision, and machine learning.
I'm interested in developing algorithms which can make use of rich sensory data such as
vision to not only make robot be able to complete complicated tasks but also improve
themselves continuously by interacting with the environment.
Learning Instance Segmentation by Experimentation
(In review) Computer Vision and Pattern Recognition (CVPR), 2018
We present a robotic system that learns to segment its visual observations into individual objects by experimenting with its environment in a completely self-supervised manner.
Zero-Shot Visual Imitation
Oral Presentation (ICLR), 2018
We present a novel skill policy architecture and dynamics consistency loss which extend visual imitation to more complex environments while improving robustness.
Probabilistically Safe Policy Transfer
International Conference on Robotics and Automation (ICRA), 2017
We formalize the idea of safe learning in a probabilistic sense by defining an optimization problem:
we desire to maximize the expected return while keeping the expected damage below a given safety limit.