ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics

By Yuanming Hu, Jiancheng Liu, A. Spielberg, Josh Tenenbaum, William T. Freeman, Jiajun Wu, Daniela Rus, Wojciech Matusik. IEEE International Conference on Robotics and Automation, 2018

318 citations recorded by the source corpus.

Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Therefore, rigid body simulators and recently their differentiable variants are studied extensively. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and there-fore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects with collisions and can be seamlessly incorporated into soft robotic systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of inference, control and co-design tasks for soft robotics.

Subfields: Computational Mechanics, Condensed Matter Physics

View Paper: https://www.semanticscholar.org/paper/dcc45df9a9291a511aaa6d33fbbf057c5e3bdc9b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Condensed Matter Physics

Josh Tenenbaum

Citations in the corpus

Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands (2022, background): “There has been significant progress in the development of differentiable physics engines [28, 33, 40, 41, 43, 44, 73, 87, 88].”
Learning to Control PDEs with Differentiable Physics (2020, background): “Specialized solvers were developed to infer protein structures (Ingraham et al., 2019), interact with liquids (Schenck & Fox, 2018), control soft robots (Hu et al., 2019), and solve inverse problems that involve cloth (Liang et al., 2019).”
DiffTaichi: Differentiable Programming for Physical Simulation (2019, methodology): “The ChainQueen differentiable elastic object simulator (Hu et al., 2019b) implements forward and gradient versions of continuum mechanics in hand-written CUDA kernels, leading to performance that is two orders of magnitude higher than a pure TensorFlow implementation.”
Visual Grounding of Learned Physical Models (2020, background): “…simulators to extract gradients (Todorov et al., 2012; Tedrake & the Drake Development Team, 2019; Degrave et al., 2019; Schenck & Fox, 2018; Hu et al., 2019; de Avila Belbute-Peres et al., 2018; Hu et al., 2020; Liang et al., 2019), which showed strong results in solving inverse problems…”
UniSim: A Neural Closed-Loop Sensor Simulator (2023, background): “Several works then developed accurate physics engines for improving robot design and motion planning [7,13,15,28,33], and for specific domains such as grasping [36], soft robotics [27], and SDVs [88].”
Challenges and Outlook in Robotic Manipulation of Deformable Objects (2021, methodology): “In the soft robotics community, SOFA [53] and Chainqueen [54] are example simulators.”