Metraipolis › archive › dc_bd37c3ca3847

KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation — arXiv:2609.18869

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18869
License (as archived)
CC0-1.0
Archived
2026-10-15T16:58:52.100Z
SHA-256 of the archived text
59a1fd44d391590ccffb55e27dde63322723b7d5ca53438e76820fde5f38caab
Stable URL of this page
https://metraipolis.com/documento/dc_bd37c3ca3847

How to cite

KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation — arXiv:2609.18869 — arXiv (en), https://arxiv.org/abs/2609.18869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd37c3ca3847 (Metraipolis archive dc_bd37c3ca3847, sha256 59a1fd44d391590ccffb55e27dde63322723b7d5ca53438e76820fde5f38caab)
BibTeX
@misc{dcbd37c3ca3847,
  title = {KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation — arXiv:2609.18869},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18869},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd37c3ca3847; sha256 59a1fd44d391590ccffb55e27dde63322723b7d5ca53438e76820fde5f38caab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid loco-manipulation requires robots to interpret task instructions and scene semantics while executing coordinated whole-body motions. We propose a hierarchical framework that uses motion keyframes as an intermediate representation between Vision-Language Model (VLM) planning and Reinforcement Learning (RL) control. Each keyframe specifies a target whole-body robot pose and, when applicable, an object pose. Given a language instruction, scene observations, and execution feedback, the VLM selects successive task-relevant keyframes from a predefined library. The selected keyframes are retargeted to the current scene to account for object poses and dimensions. A keyframe-conditioned whole-body policy then generates joint-level actions to reach these goals. We introduce a saliency-based keyframe sampling strategy for low-level policy training that improves end-to-end task success rate from 44% to 92% when using sparse VLM keyframes. We evaluate our framework on object pickup, transport, and placement tasks in simulation and on a Unitree G1 humanoid. The system successfully performs both one- and two-handed manipulation and generalises to placement locations beyond the training reference data.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.18869 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T16:13:27.331Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).