Cloth simulation has wide applications including computer animation, garment design, and robot-assisted dressing. In this work, we present a differentiable cloth simulator whose additional gradient information facilitates cloth-related applications. Our differentiable simulator extends the state-of-the-art cloth simulator based on Projective Dynamics and with dry frictional contact governed by the Signorini-Coulomb law. We derive gradients with contact in this forward simulation framework and speed up the computation with Jacobi iteration inspired by previous differentiable simulation work. To our best knowledge, we present the first differentiable cloth simulator with the Coulomb law of friction. We demonstrate the efficacy of our simulator in various applications, including system identification, manipulation, inverse design, and a real-to-sim task. Many of our applications have not been demonstrated in previous differentiable cloth simulators. The gradient information from our simulator enables efficient gradient-based task solvers from which we observe a substantial speedup over standard gradient-free methods.
翻译:克隆模拟具有广泛的应用, 包括计算机动画、 服装设计、 和机器人辅助的敷料。 在这项工作中, 我们展示了一个不同的布模拟器, 其附加的梯度信息为与布有关的应用提供了便利。 我们不同的模拟器扩展了基于预测动态和由Signriini- Coulomb 法规范的干摩擦接触的最先进的布模拟器。 我们从这个远端模拟框架中获取了梯度, 并加速了由先前不同模拟工作所启发的 Jacobi 迭代的计算。 我们最了解的是, 我们用库伦摩法提供了第一个不同的布模拟器。 我们展示了我们模拟器在各种应用中的功效, 包括系统识别、 操作、 反向设计和真实到模拟任务。 我们的许多应用程序没有在以前的不同布模拟器中展示过。 我们模拟器提供的梯度信息使得高效的梯度任务解算器能够从中观测到对标准的梯度无梯度方法的实质性加速度 。