Daniel Seita


Curriculum Vitae (July 2020)
Research Statement
Google Scholar

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 surgical robotics and assistive home robots. Please see my research statement above for additional details.

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 am originally from Albany, New York, and came to robotics at UC Berkeley through a long and winding road. Scroll down for more information.

News and Updates

Preprints and Publications

Below, you can find my publications, as well as links to code, relevant blog posts, and paper reviews. I strongly believe that researchers should make code publicly available to other researchers. Please contact me (or relevant lead authors) if a paper's code is unclear.

If a paper is on arXiv, that's where you can find the latest version. As is standard in our field, authors are ordered by contribution, and asterisks (*) represent equality.

    Preprints and Work in Progress

  1. Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks.
    Daniel Seita, Pete Florence, Jonathan Tompson, Erwin Coumans, Vikas Sindhwani, Ken Goldberg, Andy Zeng.
    November 2020.
    [Project Website and Code]

  2. Intermittent Visual Servoing: Efficiently Learning Policies Robust to Tool Changes for High-precision Surgical Manipulation.
    Samuel Paradis, Minho Hwang, Brijen Thananjeyan, Jeffrey Ichnowski, Daniel Seita, Danyal Fer, Thomas Low, Joseph E. Gonzalez, Ken Goldberg.
    November 2020.
    [arXiv] [Project Website and Code] [BibTeX]

  3. Robots of the Lost Arc: Learning to Dynamically Manipulate Fixed-Endpoint Ropes and Cables.
    Harry Zhang, Jeffrey Ichnowski, Daniel Seita, Jonathan Wang, Ken Goldberg.
    November 2020.
    [arXiv] [Project Website and Code] [BibTeX]

  4. Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics.
    Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Jennifer Grannen, Minho Hwang, Ryan Hoque, Joseph Gonzalez, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg.
    March 2020.
    [arXiv] [Project Website and Code] [BibTeX]
    We have an IROS 2020 workshop paper that extends this idea to multi-modal distributions. [arXiv]

  5. Publications in Reverse Chronological Order

  6. Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor.
    Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Kastu Yamane, Soshi Iba, John Canny, Ken Goldberg.
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2020 (virtual).
    [arXiv] [Project Website and Code] [BibTeX] [Reviews] [Blog Post]

  7. Efficiently Calibrating Cable-Driven Surgical Robots with RGBD Fiducial Sensing and Recurrent Neural Networks.
    Minho Hwang, Brijen Thananjeyan, Samuel Paradis, Daniel Seita, Jeffrey Ichnowski, Danyal Fer, Thomas Low, Ken Goldberg.
    IEEE Robotics and Automation Letters (RA-L), October 2020.
    [arXiv] [Project Website and Code] [BibTeX]

  8. VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation.
    Ryan Hoque*, Daniel Seita*, Ashwin Balakrishna, Aditya Ganapathi, Ajay Tanwani, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg.
    Robotics: Science and Systems (RSS), July 2020 (virtual).
    [arXiv] [Project Website and Code] [BibTeX] [Reviews] [Blog Post]

  9. Applying Depth-Sensing to Automated Surgical Manipulation with a da Vinci Robot.
    Minho Hwang*, Daniel Seita*, Brijen Thananjeyan, Jeffrey Ichnowski, Samuel Paradis, Danyal Fer, Thomas Low, Ken Goldberg.
    International Symposium on Medical Robotics (ISMR), April 2020 (virtual).
    [arXiv] [Project Website and Code] [BibTeX] [Reviews]

  10. 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, Vancouver, Canada.
    [arXiv] [Code] [BibTeX]

  11. 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, Hanoi, Vietnam.
    [arXiv] [Project Website and Code] [BibTeX] [Reviews] [Blog Post]

  12. Risk Averse Robust Adversarial Reinforcement Learning.
    Xinlei Pan, Daniel Seita, Yang Gao, John Canny.
    IEEE International Conference on Robotics and Automation (ICRA), May 2019, Montreal, Canada.
    [arXiv] [Project Website and Code] [BibTeX] [Reviews]

  13. 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, Brisbane, Australia.
    [arXiv] [Project Website and Code] [BibTeX] [Reviews]

  14. 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, Sydney, Australia.
    (Oral Presentation, Honorable Mention for Best Student Paper)
    [arXiv] [Code] [BibTeX] [Reviews] [Blog Post] [Slides]

  15. 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, San Francisco, United States.
    [PDF] [Code] [BibTeX] [Reviews]

  16. Computing Abelian Complexity of Binary Uniform Morphic Words.
    Francine Blanchet-Sadri*, Daniel Seita*, David Wise*.
    Theoretical Computer Science, Volume 640, June 2016.

Coursework, Teaching, and Oral Exams

I have taken many 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 and Spring 2019.
  1. (Review) CS 267, Applications of Parallel Computing
  2. (Review) CS 280, Computer Vision
  3. (Review) CS 281A, Statistical Learning Theory
  4. (Review) CS 182/282A, Deep Neural Networks (GSI/TA take two)
  5. (Review) CS 287, Advanced Robotics
  6. (Review) CS 288, Natural Language Processing
  7. (Review) CS 294-112, Deep Reinforcement Learning (now CS 285)
  8. (Review) CS 294-112, Deep Reinforcement Learning (now CS 285, self-study)
  9. (Review) CS 294-115, Algorithmic Human-Robot Interaction
  10. (Review) CS 294-129, Deep Neural Networks (GSI/TA)
  11. (Review) CS 294-131, Special Topics in Deep Learning
  12. (Review) EE 227BT, Convex Optimization
  13. (Review) EE 227C, Convex Optimization and Approximation
  14. (Review) STAT 210A, Theoretical Statistics (Classical)
  15. (Review) STAT 210B, Theoretical Statistics (Modern)
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. There is also a second oral exam, called the qualifying exam. Here is the transcript of my qualifying exam.


Here are some links that might be of interest:

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.

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.

© Daniel Seita. Last updated: November 13, 2020.