(I normally check email after 5:00PM PST.)
I am a computer science PhD student at the University of California, Berkeley.
My current research interests are an eclectic mix of robotics, deep learning, and machine teaching.
I am particularly interested in developing robotic systems for deployment in complex, unstructured environments.
For applications, I am interested in (and have experience with) surgical robotics and robot bed-making.
I am extremely fortunate to be advised by John Canny and Ken Goldberg.
I am generously supported by a National Physical Science Consortium fellowship (from 2015 to 2021), funded through the National Security Agency.
I frequently blog about technical (and non-technical) topics, and publish source code and various notes on my GitHub account.
Don't forget to also check out the Berkeley Artificial Intelligence Research blog.
I am originally from Albany, New York, and came to robotics at UC Berkeley through a long and winding road.
Quixotic though it may sound, I hope to use computer science and robotics to change the world for the better. If you have thoughts on how to do this, feel free to contact me.
News and Updates
- 10/08/2019: I attended ISRR 2019 and presented our paper.
- 10/01/2019: We have a new preprint on fabric smoothing.
- 10/01/2019: Our paper on ZPD teaching strategies has been accepted at the Deep RL workshop at NeurIPS 2019.
- 07/31/2019: Our paper on robotic cloth manipulation and bed-making has been accepted to ISRR 2019.
- 10/23/2018: We have a new blog post on the BAIR Blog about some of the work done in the AUTOLAB.
- 04/24/2018: I passed my qualifying exam. I wrote a transcript of the event and will post it online sometime in the future.
- 01/11/2018: Our paper on surgical debridement and calibration has been accepted to ICRA 2018.
- 08/16/2017: I had a great time at UAI 2017 in Sydney, Australia! I especially enjoyed giving a talk on the fourth day.
- 08/02/2017: I wrote a blog post on the BAIR Blog about our work on minibatch Metropolis-Hastings.
- 05/30/2017: I created my academic website. Sorry for the delay.
Preprints and Publications
If a paper is on arXiv, that's where you can find the latest version. (Google Scholar)
Preprints and Work in Progress
Deep Imitation Learning of Sequential Fabric Smoothing Policies.
Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Kastu Yamane, Soshi Iba, John Canny, Ken Goldberg.
[Project Website and Code]
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations.
Daniel Seita, Chen Tang, Roshan Rao, David Chan, Mandi Zhao, John Canny.
Deep Reinforcement Learning Workshop at Neural Information Processing Systems (NeurIPS), December 2019.
Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making.
Daniel Seita*, Nawid Jamali*, Michael Laskey*, Ron Berenstein, Ajay Tanwani, Prakash Baskaran, Soshi Iba, John Canny, Ken Goldberg.
International Symposium on Robotics Research (ISRR), October 2019.
Risk Averse Robust Adversarial Reinforcement Learning.
Xinlei Pan, Daniel Seita, Yang Gao, John Canny.
IEEE International Conference on Robotics and Automation (ICRA), May 2019.
Fast and Reliable Autonomous Surgical Debridement with Cable-Driven Robots Using a Two-Phase Calibration Procedure.
Daniel Seita, Sanjay Krishnan, Roy Fox, Stephen McKinley, John Canny, Ken Goldberg.
IEEE International Conference on Robotics and Automation (ICRA), May 2018.
An Efficient Minibatch Acceptance Test for Metropolis-Hastings.
Daniel Seita, Xinlei Pan, Haoyu Chen, John Canny.
Conference on Uncertainty in Artificial Intelligence (UAI), August 2017.
(Oral Presentation, Honorable Mention for Best Student Paper)
Large-Scale Supervised Learning of the Grasp Robustness of Surface Patch Pairs.
Daniel Seita, Florian T. Pokorny, Jeffrey Mahler, Danica Kragic, Michael Franklin, John Canny, Ken Goldberg.
IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), December 2016.
Computing Abelian Complexity of Binary Uniform Morphic Words.
Francine Blanchet-Sadri*, Daniel Seita*, David Wise*.
Theoretical Computer Science, Volume 640, June 2016.
Coursework and Teaching Assistantships
I've taken a number of graduate courses as part of the PhD program at UC Berkeley.
I also write reviews, which might be helpful for those thinking about taking future iterations of these classes.
I was also the GSI (i.e., Teaching Assistant) for the Deep Learning class in Fall 2016.
At the time I took it, UC Berkeley had an oral preliminary exam requirement for PhD students. Here's the transcript of my prelims. Nowadays, things might have changed since the number of AI PhD students has skyrocketed.
- (Review) CS 267, Applications of Parallel Computing
- (Review) CS 280, Computer Vision
- (Review) CS 281A, Statistical Learning Theory
- (Review) CS 182/282A, Deep Neural Networks (GSI/TA take two)
- (Review) CS 287, Advanced Robotics
- (Review) CS 288, Natural Language Processing
- (Review) CS 294-112, Deep Reinforcement Learning (now CS 285)
- (Review) CS 294-112, Deep Reinforcement Learning (now CS 285, self-study)
- (Review) CS 294-115, Algorithmic Human-Robot Interaction
- (Review) CS 294-129, Deep Neural Networks (GSI/TA)
- (Review) CS 294-131, Special Topics in Deep Learning
- (Review) EE 227BT, Convex Optimization
- (Review) EE 227C, Convex Optimization and Approximation
- (Review) STAT 210A, Theoretical Statistics (Classical)
- (Review) STAT 210B, Theoretical Statistics (Modern)
I do a fair amount of reading and running these days.
© Daniel Seita. Last updated: December 10, 2019.