PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
Zhiao Huang Yuanming Hu Tao Du
Siyuan Zhou Hao Su Joshua B. Tenenbaum Chuang Gan
Abstract
Simulated virtual environments serve as one of the main driving forces behind developing and evaluating skill learning algorithms. However, existing environments typically only simulate rigid body physics. Additionally, the simulation process usually does not provide gradients that might be useful for planning and control optimizations. We introduce a new differentiable physics benchmark called PasticineLab, which includes a diverse collection of soft body manipulation tasks. In each task, the agent uses manipulators to deform the plasticine into a desired configuration. The underlying physics engine supports differentiable elastic and plastic deformation using the DiffTaichi system, posing many underexplored challenges to robotic agents. We evaluate several existing RL methods and gradient-based methods on this benchmark. Experimental results suggest that 1) RL-based approaches struggle to solve most of the tasks efficiently; 2) gradient based approaches, by optimizing open-loop control sequences with the built-in differentiable physics engine, can rapidly find a solution within tens of iterations, but still fall short on multi-stage tasks that require long-term planning. We expect that PlasticineLab will encourage the development of novel algorithms that combine differentiable physics and model-based RL for more complex physics-based skill learning tasks.
Tasks and Reference Solutions
Quantitative Results
The final normalized incremental IoU score achieved by RL methods within 10^4 epochs. Scores lower than 0 are clamped. The dashed orange line indicates the theoretical upper limit.
Rewards and their variances in each task w.r.t. the number of episodes spent on training. We clamp the reward to be greater than 0 for a better illustration.
Qualitative Results
Move
TripleMove
Rope
Writer
Chopsticks
Torus
Pinch
Table
Assembly
RollingPin
Paper
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan
[Paper][Code][Bibtex]
Related Publications
A moving least squares material point method with displacement discontinuity and two-way rigid body coupling
Yuanming Hu, Yu Fang, Ziheng Ge, Ziyin Qu, Yixin Zhu, Andre Pradhana, and Chenfanfu Jiang
SIGGRAPH 2018
Chainqueen: A real-time differentiable physical simulator for soft robotics
Yuanming Hu, Jiancheng Liu, Andrew Spielberg, Joshua B. Tenenbaum, William T Freeman, Jiajun Wu, Daniela Rus, and Wojciech Matusik
ICRA 2019
Difftaichi: Differentiable programming for physical simulation
Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, and Fredo Durand
ICLR 2020