paper-with-me

Papers

Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

2026-05-29 · Yue Wang, Yanran Xu, Wenbo Wu, Chuanhang Qiu, Zhaoxing Li arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.31481

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Differentiable and Learnable Robot Models

2022-02-22 · Franziska Meier, Austin Wang, Giovanni Sutanto, Yixin Lin 외

Building differentiable simulations of physical processes has recently received an increasing amount of attention. Specifically, some efforts develop differentiable robotic physics engines motivated by the computational …

SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics

2026-05-08 · Yicheng Zhu, Yang Chen, Tao Li, Zilin Bian arxiv

Autonomous-driving simulators typically trade physical fidelity for scalable parallelism. Physics-based platforms such as CARLA and MetaDrive provide articulated vehicle dynamics and contact, but their non-vectorized int…

RigidFormer: Learning Rigid Dynamics using Transformers

2026-05-09 · Zhiyang Dou, Minghao Guo, Haixu Wu, Doug Roble 외 arxiv

Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-l…

Point Clouds

ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact

2020-07-02 · Moritz Geilinger, David Hahn, Jonas Zehnder, Moritz Bächer 외

We present a differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects within a unified framework. Through a principled mollification of normal and tangential contact force…

Motion Planningparameter estimationSelf-Supervised Learning

torch-sla: Differentiable Sparse Linear Algebra with Adjoint Solvers and Sparse Tensor Parallelism for PyTorch

2026-01-20 · Mingyuan Chi, Shizheng Wen arxiv

Differentiable sparse linear algebra is foundational for scientific machine learning, yet PyTorch lacks a unified library for it: torch.sparse provides only low-level kernels and a non-differentiable, CPU-only spsolve, a…