返回全部动态
NVIDIA 教机器人组装 GB300 测试托盘
原标题：The Machines that Make the Machines
AI 摘要
NVIDIA 西雅图机器人实验室与 Isaac 工程团队合作，训练机器人完成 GB300 测试托盘的母线组装和多连接器插入任务。这些任务因零件几何、外观和动态存在不确定性，且电缆会变形，自动化难度极高。团队采用经典模块化流水线（感知、规划、控制），结合 FoundationPose 等模型，最终无需转向端到端学习，并正接近富士康要求的 99.5% 成功率和 124 秒内完成的时间阈值。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
How we taught robots to assemble GB300 tester trays and what it taught us about robot learning, mechanical intelligence, and good old-fashioned engineering The NVIDIA Grace Blackwell GB300 superchip is the engine of AI training and inference for modern foundation models. However, the process of assembling GB300 trays requires skilled physical labor in factories across the world. The NVIDIA Seattle Robotics Lab (SRL), in collaboration with the NVIDIA Isaac engineering team, has asked the central
发布时间：2026-10-08 02:21
抓取时间：2026-10-08 02:53
来源机构：NVIDIA