Chelsea Finn

Graduate Student Researcher

7th Floor Sutardja Dai Hall
UC Berkeley
Berkeley, CA 94720
United States
Email Address: 

Current Research

I am a PhD student in CS at UC Berkeley, where I work on machine learning for robotic perception and control. I am a part of Berkeley AI Research Lab (BAIR), and I work with Pieter AbbeelSergey Levine, and Trevor Darrell. I recently spent time at Google Brain.  Before graduate school, I received a Bachelors in EECS at MIT, where I worked on several research projects, including an assistive technology project in CSAIL under Seth Teller and an animal biometrics project under Sai Ravela. I have also spent time at CounsylGoogle, and Sandia National Labs.


Chelsea Finn is a PhD student collaborating with Peiter Abbeel and Trevor Darrell on Berkeley DeepDrive projects.  Her research is at the intersection of machine learning, perception, and control for robotics.  In particular, she is interested in how learning algorithms can enable robots to autonomously acquire complex sensorimotor skills.


Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments
Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, Xingchao Peng, Sergey Levine, Kate Saenko, Trevor Darrell
2016. arXiv 1511.07111. [arXiv]


Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization.
Chelsea Finn, Sergey Levine, Pieter Abbeel
ICML, 2016. [Webpage] [PDF] [arXiv]

End-to-End Training of Deep Visuomotor Policies.
Sergey Levine*, Chelsea Finn*, Trevor Darrell, Pieter Abbeel
JMLR, 2016 [Webpage] [PDF] [arXiv] [code]

Deep Spatial Autoencoders for Visuomotor Learning.
Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel
ICRA, 2016. [Webpage] [PDF] [arXiv]

Learning Deep Neural Network Policies with Continuous Memory States.
Marvin Zhang, Zoe McCarthy, Chelsea Finn, Sergey Levine, Pieter Abbeel
ICRA, 2016. [PDF] [arXiv]

Bridging text spotting and SLAM with junction features.
Hsueh-Cheng Wang, Chelsea Finn, Liam Paull, Michael Kaess, Ruth Rosenholtz, Seth Teller, John Leonard
IROS, 2015. [PDF]

Beyond Lowest-Warping Cost Action Selection in Trajectory Transfer.
Dylan Hadfield-Menell, Alex Xavier Lee, Chelsea Finn, Eric Tzeng, Sandy Huang, Pieter Abbeel
ICRA, 2015.

Sloop: A pattern retrieval engine for individual animal identification.
James Duyck, Chelsea Finn, Andy Hutcheon, Pablo Vera, Joaquin Salas, Sai Ravela
Pattern Recognition, 2014.

Relevance feedback in biometric retrieval of animal photographs.
Chelsea Finn, James Duyck, Andy Hutcheon, Pablo Vera, Joaquin Salas, Sai Ravela
MCPR, 2014

Vision-Based Biometrics for Conservation
Sai Ravela, James Duyck, Chelsea Finn
MCPR, 2013

Workshop Papers:
Learning Compact Convolutional Neural Networks with Nested Dropout.
Chelsea Finn, Lisa Anne Hendricks, Trevor Darrell
International Conference on Learning Representations (ICLR) 2014. [arxiv] [PDF]

Efficient Text Detection in Human Environments.
Chelsea Finn, Nick Wang, Seth Teller
Presented at MIT EECScon, April 2014 (slides)

Class Projects:
Dual Decomposition for Efficient Optimization of Collision-Free Trajectory Warping
Chelsea Finn, Christopher Lin
UC Berkeley EE227B: Convex Optimization (pdf)