NVIDIA 发布开源机器人基础模型 GR00T 2

技术上 GR00T 2 引入 X-Adapt 机制，能从人类可穿戴设备数据和仿真等易得数据源训练，然后零样本部署到多种真实机器人本体。它还具备统一认知能力，原生集成前沿 Agent 做物理推理、错误恢复和安全监控。X-Adapt 配方将于 12 月发布。

开源范围覆盖完整技术栈：模型权重、Agent 框架、仿真引擎、标注引擎、硬件设计，以及 10 万小时（约 11 年经验）的训练数据，全部当日开放。相比多数只放权重的开源机器人项目，GR00T 2 提供了从数据到硬件的全链路复现条件，研究者和机器人创业团队可以据此搭建自己的训练流程。

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: 1. 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. 2. X-Adapt: adapting from easy data sources (human wearables and simulation) and deploying zero-shot to diverse real robots. 3. 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:

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GR00T 2, NVIDIA, 开源模型, 具身智能.

Source attribution: curated from Jim Fan (@jimfan). Cross-source corroboration: 11 independent sources have covered this development (including Decoder, NVIDIA AI, pandaily), confirming industry-wide signal strength.