跳到正文
返回论文列表
cs.GR提交于 已译

DiffGIPC: GPU 上的可微混合坐标接触动力学

DiffGIPC: Differentiable Mixed-Coordinate Contact Dynamics on GPU

Kemeng Huang · Bowen Ren · Xinyu Lu · Minchen Li · Taku komura

中文摘要

富含接触的反问题需要高效梯度及可靠的非穿透约束。现有可微方法虽能实现快速仿真与刚柔耦合,但基于惩罚或速度级约束的接触处理可能导致穿透或位置漂移。增量势能接触(IPC)通过几何屏障和连续碰撞检测(CCD)维持非穿透,但在全空间有限元(FEM)实现中,重复的前向与反向评估成本高昂,尤其是当近刚体保留大量顶点自由度(DoFs)时。DiffGIPC 是一个 GPU 加速的可微 IPC 框架,用于优化相互作用的变形体与近刚体。其仿射体导数支持静止形状设计、初始状态优化及关节控制,同时每个仿射体仅保留 12 个运动自由度。这些梯度考虑了几何、放置和驱动变化如何通过碰撞和摩擦影响其他物体。每帧保留一个耦合的 FEM-仿射伴随系统,在减少反向系统规模的同时保留驱动反问题的依赖关系。GPU 优化的反向计算进一步降低了重复梯度评估的成本。可复用的 PyTorch 接口将支持的物理参数连接到用户定义的参数映射和损失函数,涵盖设计、识别、运动、放置和关节控制。实验显示,在结合前向仿真和反向微分方面,DiffGIPC 相比 DiffIPC 在采用全空间 FEM 时峰值加速约 150.0 倍,在采用仿射体时加速 4133.3 倍。

关键要点

  1. 01现有可微接触方法基于惩罚或速度约束,存在穿透或位置漂移问题,难以满足严格非穿透要求。
  2. 02提出 DiffGIPC 框架,利用仿射体导数将每个仿射体自由度降至 12 个,支持形状、状态及关节控制优化。
  3. 03构建每帧耦合的 FEM-仿射伴随系统,保留物体间碰撞与摩擦依赖关系,避免丢弃关键物理交互。
  4. 04提供可复用 PyTorch 接口,连接物理参数与用户定义的损失函数,适用于设计、识别及运动控制等任务。
  5. 05实验表明,相比 DiffIPC,全空间 FEM 实现加速约 150.0 倍,仿射体实现加速 4133.3 倍。

解读

尚无解读。

原始英文摘要

arXiv:2610.19091v1 Announce Type: cross 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.

同方向论文 · cs.GR

查看全部 →