Jim Fan 演示 GR00T 2 端到端控制真实灵巧手
Jim Fan 发布未剪辑、1 倍速视频,展示 GR00T 2 端到端控制真实灵巧手完成任务。GR00T 2 是面向机器人的开源 System One 模型,完全运行在机器人机载算力上,支持 20+ 步、5 分钟以上的长时程灵巧操作与全身控制,可通过 X-Adapt 从人类穿戴数据和仿真零样本迁移到多种真机,并与前沿 Agent 集成实现物理推理、错误恢复和安全监控。官方开源模型权重、Agentic 框架、仿真引擎、标注引擎、硬件设计和 10 万小时训练数据(约 11 年经验),X-Adapt 配方将于 12 月发布。
Autonomous, uncut, 1x speed. This is GR00T 2 controlling real dexterous hands, end to end.
在 X 查看被引用的帖子Introducing GR00T 2: our most advanced, open System One model for robotics. It runs entirely on your robot’s onboard compute, fully untethered, and you own every weight of it. GR00T 2 features:
- Long-horizon tasks: dexterous manipulation and whole-body control chained over 20+ steps and 5+ minutes, such as performing chemistry lab experiments or assembling model airplanes end to end.
- X-Adapt: adapting from easy data sources (human wearables and simulation) and deploying zero-shot to diverse real robots.
- Unified Cognition: native integrations with frontier agents for advanced physical reasoning, robust error recovery, and safety monitoring.
It's an open-source buffet! We are releasing not only the model weights and X-Adapt recipes (coming December), but also our agentic framework, simulation engine, annotation engine, hardware design, and even training data (100K hours, that's ~11 yrs of experience), all available today!
Everything that moves will be autonomous. Anyone can become a roboticist.
Lock in, build with us!
Deep dive in thread:
来源:Jim Fan · x.com
