Metraipolis › archive › dc_cceb5c74eeed

Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation — arXiv:2611.11554

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11554
License (as archived)
CC0-1.0
Archived
2026-11-10T18:43:31.759Z
SHA-256 of the archived text
0c20915320d3aaf73e06f6a9b4f08a1828495289f26e6562b297f9f19c01ccd2
Stable URL of this page
https://metraipolis.com/documento/dc_cceb5c74eeed

How to cite

Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation — arXiv:2611.11554 — arXiv (en), https://arxiv.org/abs/2611.11554 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cceb5c74eeed (Metraipolis archive dc_cceb5c74eeed, sha256 0c20915320d3aaf73e06f6a9b4f08a1828495289f26e6562b297f9f19c01ccd2)
BibTeX
@misc{dccceb5c74eeed,
  title = {Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation — arXiv:2611.11554},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11554},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cceb5c74eeed; sha256 0c20915320d3aaf73e06f6a9b4f08a1828495289f26e6562b297f9f19c01ccd2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11554. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid loco-manipulation requires continuous coordination of high-dimensional whole-body motion to realize task objectives. While vision-language-action models and world action models transfer semantic and visual-dynamics priors to robot control, these priors do not necessarily capture the structure of robot motion. We introduce Kinematic Action Models (KAMs), a paradigm that treats whole-body motion as a direct pretraining target and uses a pretrained motion generator as the primary action-generation backbone. KAMs ground learned temporal and cross-body coordination priors through task conditioning, visual observations, and execution feedback. We present Kimodo-Policy as an initial instantiation, combining a frozen Kimodo text-to-motion backbone with lightweight ControlNet-based visual conditioning. A root-body-hand hierarchy coordinates locomotion and manipulation, while motion-history conditioning and repeated action-chunk prediction bridge motion synthesis and closed-loop control. Following large-scale loco-manipulation pretraining, the policy achieves the highest overall success among compared policies on multi-task HumanoidArena (72.14%), competitive performance on SIMPLE, and 60% mean success across eight real-world tasks, with 678M parameters (92M trainable). Ablations support the contribution of the pretrained motion backbone. Together, these results provide initial evidence for motion generation as a complementary foundation for humanoid action learning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.11554 — 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 2026-11-10T18:37:37.649Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).