本页面暂时只有英文版。
发布 · 机器人 AI · 日本

Japan's METI-backed AIRoA releases AIRoA-0 robot model trained on human recordings

The vision-language-action model learns from 16,000-plus hours of people using a handheld gripper rather than from robot teleoperation.

The YUBI handheld gripper, AIRoA's data-collection tool for the human demonstrations behind AIRoA-0, mounted on a robot arm in place of its standard gripper.Takehiko Ohkawa et al. (AIRoA) · CC BY-SA 4.0

它能做什么

Training data
16,151 hours of handheld human demonstrations
Average success, 10 two-arm tasks (AIRoA's own test)
78% (vs 27% for best rival)
The YUBI handheld gripper, AIRoA's data-collection tool for the human demonstrations behind AIRoA-0, mounted on a robot arm in place of its standard gripper. Takehiko Ohkawa et al. (AIRoA) · CC BY-SA 4.0 · 来源

The AI Robot Association (AIRoA), a Tokyo body backed by Japan's Ministry of Economy, Trade and Industry, has released AIRoA-0, a vision-language-action model that links language and vision to robot control. AIRoA lists the release date as 6 November 2026.

Its training data came from more than 16,000 hours of everyday tasks recorded with YUBI, a handheld gripper developed with Toyota, instead of demonstrations driven through a robot. It is built on Physical Intelligence's open π0.5 model. Weights are on Hugging Face under Gemma terms and the code is Apache-2.0; the training data itself has not yet been released.

Collecting data with handheld tools instead of robots is cheaper and faster, which matters for Japan's effort to build a shared data base for domestic robot makers. AIRoA reports a 78% average success rate across ten two-arm tasks, against 27% for the best of four rival models trained on the same data; no independent benchmarks are available yet.

来源

本文由 AI 根据上方来源起草,发布前经 9DOF 编辑核查。数字以来源报道为准。发现错误? 告诉我们 我们会在本页更正。

每周简报

机器人与无人机,每周一送达。

新闻 · 交易 · 活动 · 也在 TELEGRAM

每周一封邮件。第一期发出前,我们会请你确认。可随时退订。

Cookie 设置

必要登录、安全、语言、主题以及这项选择。
始终开启
隐私政策

登录

或使用邮箱