From human experience to robot action: LiberAI launches Liber-0 world-action model
From human experience to robot action: LiberAI launches Liber-0 world-action model
LiberAI has launched Liber-0, a World Action Model pretrained on more than 2.2 million hours of human experience to help robots learn physical interactions. The model combines large-scale human video with directly recorded hand motions from instrumented gloves and robot demonstrations to bridge visual, action-supervision, and embodiment gaps. In an eight-task evaluation, a policy trained with 25% robot demonstrations and 100% glove demonstrations achieved a progress score of 75.6, outperforming a policy trained on 100% robot demonstrations (score 72.8). Glove data also enabled manipulation behaviors missing from robot-only training, raising scores from 2.2 to 47.5 or 54.6 depending on the glove dataset used.
Source: Robotics & Automation News · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
score for knob turning
91.3
View original evidence
d separate policies for its LEO robot and another robot platform, Tianji, using the same glove recordings and equal amounts of teleoperation data collected for each platform. Across the three tasks, using matched glove data and equal amounts of platform-specific teleoperation data, LEO recorded scores of 91.3 for knob turning, 80.0 for arranging slippers and 100.0 for opening a drawer, compared with 76.3, 35.0 and 75
Open source S22score for arranging slippers
80
View original evidence
d separate policies for its LEO robot and another robot platform, Tianji, using the same glove recordings and equal amounts of teleoperation data collected for each platform. Across the three tasks, using matched glove data and equal amounts of platform-specific teleoperation data, LEO recorded scores of 91.3 for knob turning, 80.0 for arranging slippers and 100.0 for opening a drawer, compared with 76.3, 35.0 and 75
Open source S22score for opening a drawer
100
View original evidence
d separate policies for its LEO robot and another robot platform, Tianji, using the same glove recordings and equal amounts of teleoperation data collected for each platform. Across the three tasks, using matched glove data and equal amounts of platform-specific teleoperation data, LEO recorded scores of 91.3 for knob turning, 80.0 for arranging slippers and 100.0 for opening a drawer, compared with 76.3, 35.0 and 75
Open source S22
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
LiberAI , a physical AI startup developing foundation systems for general-purpose robots, is launching Liber-0, a World Action Model pretrained on more than 2.2 million hours of human experience to help robots learn how to interact with the physical world. Liber-0 combines large-scale human video with directly recorded hand motions, visual and embodiment alignment, and embodiment-conditioned learning, with the aim of
Open source S2
f the accumulated experience used to train the model. The longer-term objective is for that experience to produce increasingly general physical capabilities, reducing the amount of robot-specific demonstration data required to teach new behaviors. LiberAI has already tested this idea by combining robot demonstrations with glove-recorded human demonstrations. In an eight-task evaluation, a policy trained using 25 perc
Open source S16
d separate policies for its LEO robot and another robot platform, Tianji, using the same glove recordings and equal amounts of teleoperation data collected for each platform. Across the three tasks, using matched glove data and equal amounts of platform-specific teleoperation data, LEO recorded scores of 91.3 for knob turning, 80.0 for arranging slippers and 100.0 for opening a drawer, compared with 76.3, 35.0 and 75
Open source S22
Source：Robotics & Automation News · roboticsandautomationnews.com