Gpu method speeds up physics-based shape and motion optimization
DiffGIPC: Differentiable Mixed-Coordinate Contact Dynamics on GPU
GraphicsRobotics
Summary
Simulating objects touching and moving without crashing into each other, especially when they bend or almost don’t move, is tricky and slow. The authors built a method called DiffGIPC that runs on graphics cards to simulate these interactions faster and more accurately without objects sinking into each other. It also calculates exactly how changing shapes or movements affects other objects, which helps in designing shapes, controlling motions, or figuring out starting conditions. Their method is much faster than earlier ones, making complex simulations and optimizations more practical.
What this means in practice
- •For robotics engineers: Optimize robot designs and control by simulating contacts and near-rigid body motions quickly and accurately on GPUs.
- •For computer graphics developers: Create realistic, fast simulations of interacting deformable and rigid objects for animation and virtual environments.
Authors
Kemeng Huang, Bowen Ren, Xinyu Lu, Minchen Li, Taku komura
Abstract
Contact-rich inverse problems require efficient gradients and reliable enforcement of non-penetration. Existing differentiable methods provide fast simulation and rigid-deformable coupling, but contact treatments based on penalties or velocity-level constraints can permit penetration or positional drift. Incremental Potential Contact (IPC) maintains non-penetration through geometric barriers and {continuous collision detection (CCD)}. However, repeated forward and backward evaluations remain costly in full-space finite-element (FEM) implementations, particularly when nearly rigid components retain many vertex {degrees of freedom (DoFs)}. We present DiffGIPC, a GPU-accelerated differentiable IPC framework for optimizing interacting deformable and nearly rigid bodies. Our affine-body derivatives enable {rest-shape} design, initial-state optimization, and articulated control while retaining only twelve motion DoFs per affine body. These gradients account for how changes in geometry, placement, and actuation affect other objects through collision and friction. We preserve these interactions in one coupled FEM-affine adjoint system per frame, reducing the backward-system size without discarding the dependencies that drive the inverse problem. GPU-optimized backward computation further reduces the cost of repeated gradient evaluations. A reusable PyTorch interface connects supported physical parameters to user-defined parameter maps and losses across design, identification, motion, placement, and articulated control. Experiments demonstrate peak speedups over DiffIPC of approximately 150.0x with full-space FEM and 4133.3x with affine bodies for combined forward simulation and backward differentiation.