$\lambda_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation
$\lambda_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation
This research introduces HumanVerse, a 500-hour dataset of open-world human loco-manipulation, and presents $\lambda_0$, a humanoid foundation model for whole-body loco-manipulation. The dataset pairs egocentric video with synchronized body and hand motion, and the pipeline aligns camera viewpoints and arm appearance while refining motion references and controller inputs to reduce end-effector errors. The model achieves 90.0% success on SIMPLE and 62.5% on real-world loco-manipulation tasks without target-task robot demonstrations.
Source: arXiv Robotics — research abstracts · 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
Reported duration
500 hours
View original evidence
ution. We introduce HumanVerse, a 500-hour dataset of open-world human loco-manipulation pairing egocentric video with synchronized body and hand motion. Our human-to-humanoid pipeline aligns camera viewpoints and arm appearance, and refines motion references and controller inputs offline to reduce end-effector errors while preserving whole-body coordination. We validate the pipeline through zero-shot transfer to Uni
Open source S3
Dataset details reported by the source
- Modalities
- egocentric video Open source S3body and hand motion Open source S3
- Tasks
- whole-body manipulation Open source S4long-range loco-manipulation Open source S4
- Embodiments
- humanoid Open source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ution. We introduce HumanVerse, a 500-hour dataset of open-world human loco-manipulation pairing egocentric video with synchronized body and hand motion. Our human-to-humanoid pipeline aligns camera viewpoints and arm appearance, and refines motion references and controller inputs offline to reduce end-effector errors while preserving whole-body coordination. We validate the pipeline through zero-shot transfer to Uni
Open source S3
tree G1 on representative whole-body manipulation and long-range loco-manipulation tasks, without target-task robot demonstrations. Building on this pipeline, we develop $\lambda_0$, a humanoid foundation model for whole-body loco-manipulation, with robot-aligned human demonstrations providing supervision for mid-training. Increasing whole-body human data consistently improves downstream task progress. $\lambda_0$ ac
Open source S4
hieves 90.0% success on SIMPLE and 62.5% across real-world loco-manipulation tasks. We expect this study to guide scalable whole-body human data collection toward humanoid foundation models for richer interaction with the physical world. Homepage: https://lambdahumanoid.github.io/
Open source S5
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org