AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
Overview
This paper introduces AIRoA-0 (A-0), a bimanual manipulation system trained entirely on 16,151 hours of handheld demonstrations recorded using the open-source YUBI gripper, with no robot data collected during training.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · training hours: 16151 hours · Basis not reported
“arXiv:2611.03815v1 Announce Type: new Abstract: AIRoA-0 (A-0) is a bimanual manipulation system learned from 16,151 hours of handheld demonstrations, with no robot data collected at any stage. The demonstrations are recorded with YUBI, our open-source handheld gripper, which lets people record manipulation data anywhere with no robot present. From a single instruction, A-0 sorts more than a dozen small parts into the”
Exact source · revision 1Source owner not reported
Reported quantity · Reported success rate: 78 percent · reported trials
“ir numbered cells and changes the mop pads and brush of a robot vacuum; among other tasks, it unzips a pencil case and folds a towel. It performs these tasks using only a camera on each wrist, with no head or scene camera, at a site where none of its training data was recorded. Across the ten tasks of our evaluation, it averages a success rate of 78%, against 27% for the strongest of four other vision-language-action”
Exact source · revision 1Source owner not reported
Reported quantity · training time: 4 hours · Basis not reported
“it in under four hours on a single node of eight H200 GPUs.”
Exact source · revision 1Source owner not reported
Reported quantity · robots: 0 other · Basis not reported
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Reported quantity · trajectories: 0 other · Basis not reported
“arXiv:2611.03815v1 Announce Type: new Abstract: AIRoA-0 (A-0) is a bimanual manipulation system learned from 16,151 hours of handheld demonstrations, with no robot data collected at any stage. The demonstrations are recorded with YUBI, our open-source handheld gripper, which lets people record manipulation data anywhere with no robot present. From a single instruction, A-0 sorts more than a dozen small parts into the”
Exact source · revision 1Source owner not reported
Reported quantity · datasets: 0 other · Basis not reported
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Reported quantity · models: 0 other · Basis not reported
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Reported quantity · videos: 0 other · Basis not reported
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Artifact availability · weights: reported pending
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Artifact availability · dataset: reported pending
“uch as a bimanual Franka, TX-G2, OpenArm and UR. 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. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalAIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
This paper introduces AIRoA-0 (A-0), a bimanual manipulation system trained entirely on 16,151 hours of handheld demonstrations recorded using the open-source YUBI gripper, with no robot data collected during training.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).