用PyTorch实现可微分刚体动力学，让机器人学习训练速度提升64倍。
Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning
- 基于费瑟斯通算法，设计三级延迟缓存与矩阵免计算结构
- 批量处理下前向运动学提速64倍，雅可比计算提速63倍
- 适合需要高并发、自动微分的机器人强化学习研究者
随着机器人控制向大规模强化学习发展，传统依赖CPU的Pinocchio等库成为GPU训练瓶颈。本文提出BARD（Batched Articulated Rigid-body Dynamics），一个自包含的PyTorch实现，采用费瑟斯通刚体动力学算法，专为批量GPU计算和自动微分优化。三个关键设计：分层延迟缓存避免重复树遍历，预计算罗德里格斯常数实现无矩阵乘法关节变换，层级并行传播将串行操作转化为树深批处理。在5个机器人模型（7-23自由度）上，BARD数值结果与Pinocchio一致，在NVIDIA H200上批量大小4096时，前向运动学吞吐量达64倍提升，雅可比计算达63倍。通过梯度系统辨识验证可微性，在7自由度机械臂上于5%力矩噪声下质量误差均值仅1.24%。集成至Isaac Lab AMP训练流程，11自由度脊柱四足机器人4096并行环境训练中，较Pinocchio快8.5倍，较ADAM快2.0倍。代码开源：https://github.com/YueWang996/bard-pytorch-dynamics。
原文摘要 · Abstract (English)
As robot control shifts toward large-scale reinforcement learning with in-loop dynamics computation, the community's reliance on CPU-bound libraries such as Pinocchio creates a throughput bottleneck in GPU-based training pipelines. We present BARD (Batched Articulated Rigid-body Dynamics), a self-contained PyTorch implementation of Featherstone's rigid-body dynamics algorithms, optimized for batched GPU evaluation and automatic differentiation. Three design choices make this efficient: a tiered lazy-evaluation cache that avoids redundant tree traversals, matmul-free joint transforms via pre-computed Rodrigues constants, and level-parallel propagation that reduces sequential operations to tree-depth batched steps. On five robot models (7-23 DOFs), BARD matches Pinocchio numerically while reaching up to 64x higher throughput for Forward Kinematics and 63x for Jacobians at batch size 4096 on an NVIDIA H200. We validate differentiability through gradient-based system identification on a 7-DOF manipulator, recovering link masses to 1.24% mean error under 5% torque noise, and integrate BARD into an Isaac Lab AMP training pipeline for an 11-DOF spined quadruped with 4096 parallel environments, where it is 8.5x faster than Pinocchio and 2.0x faster than ADAM for in-loop dynamics. BARD is open-sourced at: https://github.com/YueWang996/bard-pytorch-dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。