Yunsheng Tian

Yunsheng Tian

PhD Candidate

MIT CSAIL

Yunsheng Tian is a final-year PhD student in the Computational Design & Fabrication Group at MIT CSAIL advised by Prof. Wojciech Matusik. His current research aims at:

  1. Building generalizable and adaptive robotic systems for complex industrial/household manipulation tasks, leveraging the power of physical simulation, planning, and learning;
  2. Developing data-efficient global optimizers involving multiple unknown objectives and constraints for general real-world applications.

Before coming to MIT, he obtained the bachelor’s degree from Nankai University, advised by Prof. Bo Ren and Prof. Ming-Ming Cheng. He had also worked at MIT-IBM Watson AI Lab, Autodesk Research, The University of Hong Kong and Microsoft Research Asia as a research intern.

News: We are organzing Workshop on Learning Robotic Assembly of Industrial and Everyday Objects at CoRL 2024!

Interests

  • Robotics 🤖
  • Machine Learning 🧠
  • Computer Graphics 🎨

Education

  • PhD in Computer Science, 2019 - Present

    Massachusetts Institute of Technology, MA, U.S.

  • BEng in Software Engineering, 2015 - 2019

    Nankai University, Tianjin, China

Publications

ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility 🤖 🧠

International Conference on Robotics and Automation (ICRA) 2024
Robotic assembly plan generation for complex and general-shaped assemblies.
ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility

Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints 🧠

International Conference on Machine Learning (ICML) 2024
Efficient global optimizer for physical designs with unknown constraints.
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints

Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly 🤖 🎨

ACM Transactions on Graphics (SIGGRAPH Asia) 2022
Physics makes motion planning for complex assemblies simple, fast, and generalizable.
Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly

JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints 🧠 🎨

Computer Vision and Pattern Recognition (CVPR) 2022
Learning to assemble on a big CAD assembly dataset approaching human-level accuracy.
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints

Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots 🤖

Neural Information Processing Systems (NeurIPS) 2021
The first and largest benchmark for evolving soft robot morphology.
Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots

Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations 🧠

Neural Information Processing Systems (NeurIPS) 2020
Efficient multi-objective optimizer for expensive black-box functions.
Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations

Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control 🧠 🤖

International Conference on Machine Learning (ICML) 2020
Efficient multi-objective RL for discovering all Pareto-optimal policies.
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

Fluid Directed Rigid Body Control using Deep Reinforcement Learning 🤖 🎨

ACM Transactions on Graphics (SIGGRAPH) 2018
Deep RL can control high-dimensional fluid-rigid coupling dynamics.
Fluid Directed Rigid Body Control using Deep Reinforcement Learning

Workshop Papers

Towards Generalizable and Adaptive Multi-Part Robotic Assembly 🤖

Robotics: Science and Systems (RSS) 2024 GAS Workshop
A general dual-arm robotic system that end-to-end assembles multiple parts.
Towards Generalizable and Adaptive Multi-Part Robotic Assembly

AutODEx: Automated Optimal Design of Experiments Platform with Data- and Time-Efficient Multi-Objective Optimization 🧠

Neural Information Processing Systems (NeurIPS) 2023 RealML Workshop
Easy-to-use experimental design platform based on asynchronous multi-objective BO.
AutODEx: Automated Optimal Design of Experiments Platform with Data- and Time-Efficient Multi-Objective Optimization

Accelerated High-Entropy Alloys Discovery for Electrocatalysis via Robotic-Aided Active Learning 🧠 🤖

Neural Information Processing Systems (NeurIPS) 2023 RealML Workshop
(Best Student Paper)
Accelerated scientific discovery through active learning and autonomous robots.
Accelerated High-Entropy Alloys Discovery for Electrocatalysis via Robotic-Aided Active Learning

Projects

Autonomous Robotic Assembly of a Skateboard Truck 🤖

Autodesk Research Project 2023
Autonomous assembly of a mechanical skateboard truck with a flexible robotic system.
Autonomous Robotic Assembly of a Skateboard Truck

Experience

 
 
 
 
 

Research Intern

MIT-IBM Watson AI Lab

Jun 2024 – Aug 2024 Cambridge, MA, U.S.
Advised by Prof. Chuang Gan
 
 
 
 
 

Research Intern

AI Lab, Autodesk Research

May 2023 – Aug 2023 San Francisco, CA, U.S.
Advised by Dr. Jieliang Luo
 
 
 
 
 

Research Assistant

Computational Design & Fabrication Group, MIT CSAIL

Aug 2019 – Present Cambridge, MA, U.S.
 
 
 
 
 

Research Assistant

Department of Computer Science, The University of Hong Kong

Feb 2019 – May 2019 Hong Kong, China
Advised by Prof. Jia Pan
 
 
 
 
 

Research Intern

Visual Computing Group, Microsoft Research Asia

Jul 2018 – Sep 2018 Beijing, China
 
 
 
 
 

Research Assistant

Media Computing Lab, Nankai University

Apr 2016 – Jun 2019 Tianjin, China

Services

Conference Reviewer: SIGGRAPH/SIGGRAPH Asia, CoRL, ICRA, IROS, ICLR, ICML, NeurIPS, AISTATS

Journal Reviewer: RA-L, TVCG, TEVC, Soft Computing, TMLR

Invited Talks:

  • [2024/07] DigitalFUTURES Workshop: “Towards Generalizable and Adaptive Robotic Assembly of Industrial and Everyday Objects”
  • [2023/11] Tsinghua University IIIS Seminar: “Towards Automated Planning and Execution for Generalizable and Complex Robotic Assembly”
  • [2023/08] Autodesk Research Connections: “Physics-Based Planning for Automated Robotic Assembly”
  • [2023/03] MIT Graphics Seminar: “Physics-Based Planning for Automating Contact-Rich Assembly”
  • [2021/04] MIT CSAIL Alliances Tech Workshop: “Automated Multi-Objective Optimal Experiment Design Platform”
  • [2020/11] Lam Research Seminar: “Multi-Objective Bayesian Optimization for Adaptive Experimental Design”

Teaching and Mentoring:

  • [Fall 2023] Teaching Assistant for MIT EECS Advanced Computer Graphics/Computational Design and Fabrication
  • [Fall 2020 - Present] Research Mentor of 8 students participating in MIT UROP (Undergraduate Research Opportunities Program)

Awards

  • [2023] Zetta Prize - Best Application of Artificial Intelligence in Industry: First place, given by MIT Machine Intelligence for Manufacturing & Operations Symposium
  • [2019] Outstanding Graduate: Top 4% among all students, given by Nankai University
  • [2016-2017] National Scholarship: Top 2% among all students, given by Ministry of Education of China

Contact

  • yunsheng [at] csail [dot] mit [dot] edu
  • 32 Vassar Street, 321, Cambridge, MA 02139