arXiv · cs.AI · Yueh-Hua Wu, Kei Ota, Hanlong Li, Hayata Yuasa, Jason Wang, Kengo Ikeuchi, Kensuke Chiyoma, Makoto Sugiura, Masafumi Takahashi, Masatoshi Tateno, Naoaki Kanazawa, Nicola Scianca, Petr Khrapchenkov, Satoshi Otsubo, Takehiko Ohkawa, Takuya Okubo, Tatsuya Matsushima, Yuki Noguchi, Yuma Shin, Zixuan Zhong · 3 小时前模型评分74
AIRoA-0 发布：仅用手持夹爪数据训练双臂操作，十项任务平均成功率 78%
AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
导读
AIRoA-0（A-0）是一个从 16,151 小时手持演示中学习、全程不采集机器人数据的双臂操作系统。它只靠双腕摄像头完成任务，在十项评测中平均成功率 78%，而同样用这些演示做后训练的四个视觉语言动作模型中最强的一个为 27%。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：data-resources、foundation-models，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We are releasing the dataset, to our knowledge the largest open dataset of handheld-gripper demonstrations with task and subtask instructions, together with the pre-trained weights and the post-training recipe.”
- “Anyone can build the gripper, record a task of their own and post-train the model on it in under four hours on a single node of eight H200 GPUs.”
来源：arXiv · cs.AI · arxiv.org