面向基于GPU的模拟器中非凸物体高效仿真的局部物体裁剪碰撞网络
Local object crop collision network for efficient simulation of non-convex objects in GPU-based simulators
AI总结：
针对GPU模拟器中非凸物体接触检测速度与精度难以兼顾的问题，提出基于局部物体裁剪形状学习的数据驱动碰撞检测算法，在精度相当的情况下将效率提升5-10倍，集成到Brax后兼具优于IsaacGym的效率和优于标准Brax的通用性。
摘要：
我们的目标是开发一种高效的接触检测算法，用于基于GPU的大规模非凸物体仿真。当前基于GPU的模拟器（如IsaacGym和Brax）在仿真非凸物体时，必须在速度与保真度、通用性之间权衡，或同时牺牲二者。其核心问题在于接触检测（CD）：现有接触检测算法（如Gilbert-Johnson-Keerthi (GJK)）必须在计算速度与精度间权衡，随着非凸物体间碰撞数量增加，计算成本会变得极高。我们提出一种数据驱动的接触检测方法，其精度仅取决于离线数据集的质量和数量，而非在线计算时间。与GJK不同，我们的方法天然具备统一的计算流，可借助XLA（加速线性代数）等高级编译器实现高效的GPU利用。此外，我们通过学习碰撞的局部裁剪物体形状模式（而非更难学习的全局物体形状），提供了一种数据高效的解决方案。实验表明，对于非凸物体，我们的方法在精度相当的情况下，将现有接触检测方法的效率提升了5-10倍。结合此前基于神经网络的接触检测器的接触求解研究，我们将该接触检测算法集成到开源GPU模拟器Brax中，验证了其效率优于IsaacGym、通用性优于标准Brax。我们强烈推荐查看补充材料中包含的模拟器演示视频。
英文摘要：
Our goal is to develop an efficient contact detection algorithm for large-scale GPU-based simulation of non-convex objects. Current GPU-based simulators such as IsaacGym and Brax must trade-off speed with fidelity, generality, or both when simulating non-convex objects. Their main issue lies in contact detection (CD): existing CD algorithms, such as Gilbert-Johnson-Keerthi (GJK), must trade off their computational speed with accuracy which becomes expensive as the number of collisions among non-convex objects increases. We propose a data-driven approach for CD, whose accuracy depends only on the quality and quantity of offline dataset rather than online computation time. Unlike GJK, our method inherently has a uniform computational flow, which facilitates efficient GPU usage based on advanced compilers such as XLA (Accelerated Linear Algebra). Further, we offer a data-efficient solution by learning the patterns of colliding local crop object shapes, rather than global object shapes which are harder to learn. We demonstrate our approach improves the efficiency of existing CD methods by a factor of 5-10 for non-convex objects with comparable accuracy. Using the previous work on contact resolution for a neural-network-based contact detector, we integrate our CD algorithm into the open-source GPU-based simulator, Brax, and show that we can improve the efficiency over IsaacGym and generality over standard Brax. We highly recommend the videos of our simulator included in the supplementary materials.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
