Yide(Fred) Shentu

fredshentu at berkeley dot edu

I am a Machine Learning Engineer working at Covariant AI. Previously, I graduated from UC Berkeley majoring in Computer Science and Physics. During my undergraduate study, I worked as an undergraduate research assistant in Berkeley Artificial Intelligence Research (BAIR) Lab. I worked with Professor Pieter Abbeel,Professor Sergey Levine, Professor Alexei Efros, Professor Jitendra Malik and Professor Trevor Darrell.

Email  /  CV  /  Github


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

Dian Chen*, Yide Shentu*, Deepak Pathak*, Pulkit Agrawal*, Trevor Darrell, Segry Levine, Jitendra Malik
(In review) Computer Vision and Pattern Recognition (CVPR), 2019
website, pdf

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

Deepak Pathak*, Parsa Mahmoudieh*, Michael Luo*, Pulkit Agrawal*, Dian Chen, Yide Shentu, Evan Shelhamer, Alexei Efros, Trevor Darrell
Oral Presentation (ICLR), 2018
website, pdf

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

David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel
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.