RoboFin3D：用于机器人表面处理的仿真到现实平台
RoboFin3D: A Sim-to-Real Platform for Robotic Surface Finishing
浏览论文内容
中文总结 AI 辅助
RoboFin3D是基于Isaac Sim和Newton物理引擎的仿真到现实平台，通过SDF建模工件几何和表面场模拟外观变化，并引入WeldGen生成多样资产，校准后仿真数据提升感知模型性能，如SAM2分割IoU从77.15%提升至97.41%。
中文摘要 AI 辅助
磨削和砂磨是工业机器人表面处理中的基础工艺。然而，物理试验成本高昂且消耗工件，使得可重复实验变得困难。我们提出了RoboFin3D，一个基于Isaac Sim和Newton物理引擎的仿真到现实平台，为低成本、可重复的机器人表面处理实验提供基于物理的磨削和砂磨仿真。RoboFin3D利用符号距离场（SDF）对工件不断变化的几何形状进行建模，无需中间网格即可实现接触计算、实时更新和渲染。此外，它还使用一个独立的表面场来模拟砂磨过程中表面外观的渐进变化。我们还引入了WeldGen，一个焊缝采样模块，用于在8,918个真实世界工件网格上生成焊缝，以提供多样化的仿真资产。仿真参数根据真实实验结果进行校准，我们的评估证明了我们的仿真相对于真实世界的保真度。我们还展示了仿真生成的数据可用于提升感知模型的性能。仅使用仿真数据对SAM2进行微调，将未砂磨区域分割的IoU从77.15%提升至84.47%，而结合合成数据和真实数据训练则达到97.41%。
英文摘要
Grinding and sanding are fundamental processes in industrial robotic surface finishing. However, physical trials are expensive and consume workpieces, making reproducible experiments difficult. We present RoboFin3D, a sim-to-real platform built on Isaac Sim and the Newton physics engine, that provides physics-based grinding and sanding simulation for cheap and repeatable robotic surface finishing experiments. RoboFin3D utilizes a signed distance field (SDF) to model the changing geometry of the workpiece, enabling contact computation, live updates and rendering without an intermediate mesh. It additionally uses a separate surface field to model progressive surface appearance change during sanding. We also introduce WeldGen, a weld sampling module, to generate weld beads on 8,918 real-world workpiece meshes for providing diverse simulation assets. The simulation parameters are calibrated on real experimental results and our evaluation demonstrates our simulation's fidelity against the real world. We also demonstrate that simulation-generated data can be used to improve the performance of perception models. Simulation-only fine-tuning of SAM2 improves IoU for segmentation of unsanded regions from 77.15% to 84.47%, while combined synthetic and real training reaches 97.41%.
发表机构
- Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。
