DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes

11/30/2021
by   Michael Strecke, et al.
0

Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions. Existing approaches have frequently been limited to objects with simple shape or shapes that are known in advance. In this paper, we propose a novel approach to differentiable physics with frictional contacts which represents object shapes implicitly using signed distance fields (SDFs). Our simulation supports contact point calculation even when the involved shapes are nonconvex. Moreover, we propose ways for differentiating the dynamics for the object shape to facilitate shape optimization using gradient-based methods. In our experiments, we demonstrate that our approach allows for model-based inference of physical parameters such as friction coefficients, mass, forces or shape parameters from trajectory and depth image observations in several challenging synthetic scenarios and a real image sequence.

READ FULL TEXT

page 8

page 13

page 17

page 18

page 19

page 20

page 21

page 22

research
09/09/2023

Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contact

We present Jade, a differentiable physics engine for articulated rigid b...
research
04/09/2020

Where Does It End? – Reasoning About Hidden Surfaces by Object Intersection Constraints

Dynamic scene understanding is an essential capability in robotics and V...
research
02/12/2018

Geodesic Convolutional Shape Optimization

Aerodynamic shape optimization has many industrial applications. Existin...
research
12/07/2022

Learning rigid dynamics with face interaction graph networks

Simulating rigid collisions among arbitrary shapes is notoriously diffic...
research
10/28/2021

Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language

In this work, we propose a unified framework, called Visual Reasoning wi...
research
01/02/2019

Learning Generalizable Physical Dynamics of 3D Rigid Objects

Humans have a remarkable ability to predict the effect of physical inter...
research
05/27/2019

Physics-as-Inverse-Graphics: Joint Unsupervised Learning of Objects and Physics from Video

We aim to perform unsupervised discovery of objects and their states suc...

Please sign up or login with your details

Forgot password? Click here to reset