AI News

NVIDIA Releases World Action Model GR00T 2 and Launches Isaac Lab 3.0

English text is being prepared.Updated Nov 10 12:32

English text is being prepared.

AI summary

NVIDIA has released its new-generation world action model GR00T 2, which can simultaneously predict future video frames and robot actions. Its pretraining used over 400,000 hours of first-person human video, about 10,000 hours of handheld gripper demonstrations, and 23,500 hours of robot teleoperation data. Across 50 tasks that the target robot had not been trained on before, GR00T 2 achieved an average zero-shot success rate of 40%; after providing one demonstration per task, the average success rate rose to 71%, and after five demonstrations plus fine-tuning, it reached 95%. NVIDIA also introduced the robot learning framework Isaac Lab 3.0, which integrates the Newton physics engine and achieves up to 2.5 times higher training throughput than previous solutions in vision-driven dexterous manipulation benchmarks.

Why read this

AI score 70

The original text provides zero-shot success rates, the number of demonstrations, and the improvement curve after fine-tuning, which can be used to assess how usable this world action model is on real tasks.

Topics

Tags

Body

编译/VR陀螺

11月9日,英伟达发布新一代世界动作模型GR00T 2,并介绍机器人学习框架Isaac Lab 3.0及多项机器人训练与评测技术。

据悉,GR00T 2采用世界动作模型架构,能够同时预测未来视频画面与机器人动作,使机器人能够根据指令执行操作,还能学习动作对物理环境产生的影响。

据英伟达披露,GR00T 2使用超过40万小时人类第一视角视频、约1万小时手持夹爪演示及2.35万小时机器人遥操作数据进行预训练,支持将人类示范学习到的技能迁移至不同机器人本体。

在50项目标机器人此前未训练过的任务中,GR00T 2零样本平均成功率达到40%,其中40项任务至少成功完成一次。每项任务仅提供一次演示,平均成功率便提升至71%;增加至五次演示,并经过微调后,成功率进一步达到95%。

精细操作方面,搭载双22自由度灵巧手的机器人已能够完成GB300内存模块安装、玩具卡车组装等任务,对应测试成功率分别达到85%和65%。英伟达还展示了机器人通过人类示范学习实验室操作、利用强化学习改善插接任务表现的能力。

与此同时,Isaac Lab 3.0进一步整合Newton物理引擎,支持线缆、布料等可变形物体及复杂机械关节仿真。在视觉驱动的灵巧操作基准测试中,其训练吞吐量较此前方案最高提升2.5倍。

产业应用方面,富士康正将GR00T 2应用于服务器制造自动化,西门子正在评估其工业应用潜力,Nexuni则开展机器人衣物处理测试。

投稿/爆料:tougao@youxituoluo.com

稿件/商务合作: 林南(微信 19250561593)

加入行业交流群:林南(微信 19250561593)

数字科技产业资讯与服务平台

下载「陀螺科技」APP,获取前沿深度数字科技产业讯息

Source

English text is being prepared.