Publications      (* denotes equal contribution)
|
|
UniInsertion: A Unified Model-Based Insertion Skill
Learning via Differentiable
Physics-Based Simulation
Chenrui Tie, Wang Debang, Gaurav Chaudhary, Weikun Peng, Tianyi Chen, Gang Yang, Yao Mu, Lin Shao
In Submission
We proposed a new task set, including a class of common "soft insertion" tasks in real life, where both the object to be inserted
and the container can be deformable. We utilized a differentiable simulator design framework to
enable robots to acquire the skills rapidly.
|
|
Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contact
Gang Yang, Siyuan Luo, Yunhai Feng, Zhixin Sun, Chenrui Tie,
Lin Shao
ICRA 2024 (Under Review)
[paper]
[project page]
We developed Jade, a differentiable physics engine
for articulated rigid bodies, using the continuous collision
detection to detect the time of impact for collision checking
and adopt the backtrack strategy to prevent intersection
between bodies with complex geometry shapes. We also derived
the gradient calculation to ensure the whole simulation
process differentiable under the backtrack mechanism.
|
|
Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly
Ruihai Wu*,
Chenrui Tie*,
Yushi Du,
Yan Zhao,
Hao Dong
ICCV 2023
[paper]
[project page]
We tackle multi-part geometrically assembly task, leveraging SE(3) equivariance and invariance,
which
fits the physics of the task and narrows the solution space. Thus our method performs better than
previous
methods in two datasets, and is intuitive to future works.
|
2023.4 - now Research Assistant, Shao Lin's Lab, National University of Singapore
- Improvement and application of differential simulator
- Sim2real adaptation
- Supervisor: Prof. Lin Shao
2022.12 - 2023.3 Research Assistant, Hyperplane lab, Peking University
- SE(3) equivariant geometric part assembly
- Supervisor: Prof. Hao Dong
- Collaborated with Ruihai Wu
2022.2 - 2022.11 Research Assistant, EPIC lab, Peking University
- Model based reinforcement learning for articulated object manipulation on real robot
- Supervisor: Prof. He Wang
- Familiarity with common reinforcement learning algorithms and the control of the Franka robot
arm
2021.7 - 2022.2 Research Assistant, EPIC lab, Peking University
- Physics intuitive learning
- Supervisor: Prof. He Wang
|
Peking University, Beijing, China
Sept 2021 - Present (Expected 2024), Undergraduate Student, Department of Intelligent Science
- Advisor: Prof. Hao Dong, Prof. He Wang
- Lab: Hyperplane Lab and Epic Lab, Center on Frontiers of Computing Studies
Peking University, Beijing, China
Sept 2019 - June 2021, Undergraduate Student, School of Physics
|
Language: Chinese: native English: IELTS 7.0 TOEFL 106
Deep Learning Frameworks: PyTorch (Proficient)
Simulators: SAPIEN, ISAAC GYM, Nimble, DiffCloth, Jade
Real Robot Development Experience:Franka, Flexiv rizon
Background Knowledge: Physics, Robotics, Differential Simulation, Reinforcement Learning, Computer Vision
|
Demonstration physics, 2023
|
Lee Wai Wing Scholarship (top 20%) Peking University, 2023
Merit Student award,     Peking University, 2023
Merit Student award,     Peking University, 2022
Achievement Improvement award,     Peking University, 2021
Qin-Jin Scholarship,     Peking University, 2020
First prize in National High School Math League in Provinces,     China Mathematical
Society, 2018
|
Website template comes from Jon Barron
Last update: Nov, 2023
|
|