portrait

About Me

I am a final-year Ph.D. student at MIT CSAIL advised by Wojciech Matusik. My research lies at the intersection of computer graphics, robotics, and machine learning. I develop computational methods to solve challenging design and control problems in complex physical systems. Some of my research topics include building differentiable physics simulation environments for inverse design and control of robots, developing end-to-end pipelines for co-optimizing shape and control of real robots, and exploring continuous Pareto fronts in multi-objective optimization and multi-task learning.

Research Interests

Graphics: computational design and fabrication, (differentiable) physics simulation, shape analysis
Robotics: aerial robots, soft robots
Learning: differentiable physics, multi-task learning, sim-to-real transfer

News

04/2021: I will talk about simulation and robotics in the Computational Fabrication Seminar on April 21 [Video].
04/2021: Two papers conditionally accepted to SIGGRAPH 2021.


Publications

(* indicates equal contributions)

DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation

Pingchuan Ma, Tao Du, John Z. Zhang, Kui Wu, Andrew Spielberg, Robert K. Katzschmann, Wojciech Matusik. SIGGRAPH 2021 (ACM Transactions on Graphics)

[Project] [Paper] [Code (Coming soon)]

Underwater Soft Robot Modeling and Control with Differentiable Simulation

Tao Du*, Josie Hughes*, Sebastien Wah, Wojciech Matusik, Daniela Rus. RA-L/RoboSoft 2021

[Project] [Paper] [Code (Coming soon)] [Poster]

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan. ICLR 2021 (Spotlight)

[Project] [Paper] [Code]

Efficient Continuous Pareto Exploration in Multi-Task Learning

Pingchuan Ma*, Tao Du*, Wojciech Matusik. ICML 2020

[Project] [Paper] [Supplement] [Code] [Talk] [Slides]

Learning-in-the-Loop Optimization: End-to-End Control and Co-Design of Soft Robots through Learned Deep Latent Representations

Andrew Spielberg, Allan Zhao, Tao Du, Yuanming Hu, Daniela Rus, Wojciech Matusik. NeurIPS 2019

[Project] [Paper]

Learning to Fly: Computational Controller Design for Hybrid UAVs with Reinforcement Learning

Jie Xu, Tao Du, Michael Foshey, Beichen Li, Bo Zhu, Adriana Schulz, Wojciech Matusik. SIGGRAPH 2019 (ACM Transactions on Graphics)

[Project] [Paper] [Code]


Talks

Differentiable Simulation Methods for Robotic Agent Design

A seminar talk summarizing our thoughts on differentiable simulators and their applications in real-world robotic problems.

[Slides] [Video]


Press


Miscellaneous

A Practical Guide to Building a Pentacopter

A step-by-step document that explains how to design, simulate, control, and build a pentacopter for drone hobbyists.

[Document (design)] [Document (control)] [Video]

Age of Empires 2

My favorite video game for over 15 years. I am among the top 20-25% players (1v1 random maps) on the Internet and am working hard to become a Pareto optimal solution to {max(research), max(AoE2 ELO)} in the union set of graphics PhDs and AoE2 players across the world.