I am a fourth-year Ph.D. student in the Robust Robotics Group at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, advised by Prof. Nicholas Roy. I am very grateful for the support from the NSF Graduate Research Fellowship.

My research is motivated by a dream experiment I hope to try someday: let a robot run unattended for a long while (~years) with an algorithm that learns the world’s structure, so we can peek inside the robot’s head to see how complicated everyday life is. We’ve yet to see robots capable of that experiment, though. My work draws upon ideas from many areas, including task and motion planning (TAMP) and algorithmic statistics, to design learning algorithms and reasoning systems necessary for robots to complete such an arduous task.

Previously, I completed a joint concentration in mathematics and computer science at Brown University and was advised by Prof. George Konidaris and Prof. Stefanie Tellex. I was also a research intern at MERL.

When I’m not working on research, you can find me running (not so quickly) and occasionally bike touring. I am also an observant Jew, which may affect my availability online (is it a Jewish holiday today?).

Publications

* equal contribution.

Preprints

• Towards Practical Finite Sample Bounds for Motion Planning in TAMP
  Seiji Shaw, Aidan Curtis, Leslie Pack Kaelbling, Tomás Lozano-Pérez, and Nicholas Roy
  Algorithmic Foundations of Robotics (in press), 2024.
  arxiv. code.

Conferences

• Constrained Bimanual Planning with Analytic Inverse Kinematics
  Thomas Cohn, Seiji Shaw, Max Simchowitz, and Russ Tedrake
  IEEE International Conference on Robotics and Automation, 2024.
  Best Paper in Robot Manipulation Finalist.
  link. arxiv.
• Amortized Inference for Efficient Grasp Model Adaptation
  Michael Noseworthy*, Seiji Shaw*, Chad C. Kessens, and Nicholas Roy
  IEEE International Conference on Robotics and Automation, 2024.
  link. arxiv.
• Constrained Dynamic Movement Primitives for Collision Avoidance in Novel Environments
  Seiji Shaw, Devesh K. Jha, Arvind U. Raghunathan, Radu Corcodel, Diego Romeres, George Konidaris, and Daniel Nikovski
  IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023.
  link. arxiv.
• RMPs for Safe Impedance Control in Contact-Rich Manipulation
  Seiji Shaw, Ben Abbatematteo, and George Konidaris
  IEEE International Conference on Robotics and Automation, 2022.
  link. arxiv.

Workshop Manuscripts

• Learning Attentive Neural Processes for Planning with Pushing Actions
  Atharv Jain, Seiji Shaw, and Nicholas Roy
  Robotics: Science and Systems RoboReps Workshop, 2025.
  arxiv.

Contact

seijis [at] mit [dot] edu

Office: 45-633, Schwarzman College of Computing (Building 45), MIT