SDFを用いた微分可能剛体力学シミュレータ
DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes
物体形状を符号付き距離場(SDF)で陰的に表現し、摩擦接触を含む微分可能な剛体物理シミュレーションを実現。形状・摩擦係数・質量などを軌跡や深度画像から推定できることを示した。
著者: Michael Strecke, Joerg Stueckler
分類: cs.CV, cs.GR, cs.LG, cs.RO
原文アブストラクト
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.
