合成场景训练实现人形机器人全身操控

Skip to main content

arXiv is now an independent nonprofit!Learn more×

Search arXiv

Press Enter to search ·Advanced search

Computer Science > Robotics

arXiv:2606.30645v1 (cs)

[Submitted on 29 Jun 2026]

Title:VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

Authors:Yen-Jen Wang,Jiaman Li,Sirui Chen,Takara E. Truong,Pei Xu,Pieter Abbeel,Rocky Duan,Koushil Sreenath,Angjoo Kanazawa,Carmelo Sferrazza,Guanya Shi,Karen Liu

View a PDF of the paper titled VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes, by Yen-Jen Wang and 11 other authors

View PDFHTML (experimental)

Abstract:Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion. Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale. We address this bottleneck by generating vision-language-kinematics (VLK) supervision synthetically in reconstructed scenes. Our pipeline leverages 3D Gaussian Splatting to reconstruct metric-scale indoor environments, synthesizes navigation and object-interaction trajectories using privileged scene information, and renders paired egocentric observations after the fact. We produce 48,000 paired trajectories with no human intervention and train a VLK policy that predicts short-horizon whole-body kinematic trajectories. A whole-body tracker converts these predictions into actions on the physical humanoid. We evaluate on the physical Unitree G1 performing navigation and single-object transport, demonstrating that synthesized interactions in reconstructed scenes provide effective supervision for sim-to-real perception-based humanoid loco-manipulation. Project Website:this https URL

| | | | --- | --- | | Comments: | 19 pages, 7 figures, 4 tables | | Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Graphics (cs.GR); Systems and Control (eess.SY) | | Cite as: |arXiv:2606.30645[cs.RO] | | | (orarXiv:2606.30645v1[cs.RO] for this version) | | |https://doi.org/10.48550/arXiv.2606.30645<br>Focus to learn more<br>arXiv-issued DOI via DataCite |

Submission history

From: Yen-Jen Wang \[view email]

[v1] Mon, 29 Jun 2026 17:59:55 UTC (6,941 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes, by Yen-Jen Wang and 11 other authors

• View PDF
• HTML (experimental)
• TeX Source


Current browse context:

cs.RO

[< prev](https://arxiv.org/prevnext?id=2606.30645&function=prev&context=cs.RO "previous in cs.RO (accesskey p)")  \|  [next >](https://arxiv.org/prevnext?id=2606.30645&function=next&context=cs.RO "next in cs.RO (accesskey n)")

new\|recent\|2026-06

Change to browse by:

cs

cs.AI

cs.GR

cs.SY

eess

eess.SY

References & Citations

• NASA ADS
• Google Scholar
• Semantic Scholar

export BibTeX citation

Bookmark


Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer _(What is the Explorer?)_

Connected Papers Toggle

Connected Papers _(What is Connected Papers?)_

Litmaps Toggle

Litmaps _(What is Litmaps?)_

scite.ai Toggle

scite Smart Citations _(What are Smart Citations?)_

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv _(What is alphaXiv?)_

Links to Code Toggle

CatalyzeX Code Finder for Papers _(What is CatalyzeX?)_

DagsHub Toggle

DagsHub _(What is DagsHub?)_

GotitPub Toggle

Gotit.pub _(What is GotitPub?)_

Huggingface Toggle

Hugging Face _(What is Huggingface?)_

ScienceCast Toggle

ScienceCast _(What is ScienceCast?)_

Demos

Demos

Replicate Toggle

Replicate _(What is Replicate?)_

Spaces Toggle

Hugging Face Spaces _(What is Spaces?)_

Spaces Toggle

TXYZ.AI _(What is TXYZ.AI?)_

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower _(What are Influence Flowers?)_

Core recommender toggle

CORE Recommender _(What is CORE?)_

• Author
• Venue
• Institution
• Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.

Which authors of this paper are endorsers?\| Disable MathJax (What is MathJax?)