Metraipolis › archive › dc_73da559fbe0c

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References — arXiv:2611.09266

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09266
License (as archived)
CC0-1.0
Archived
2026-11-09T22:46:02.489Z
SHA-256 of the archived text
651349b4c353d84c9c18408e77704eff75407f4dc6b0ba6bf279647aeafc47eb
Stable URL of this page
https://metraipolis.com/documento/dc_73da559fbe0c

How to cite

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References — arXiv:2611.09266 — arXiv (en), https://arxiv.org/abs/2611.09266 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73da559fbe0c (Metraipolis archive dc_73da559fbe0c, sha256 651349b4c353d84c9c18408e77704eff75407f4dc6b0ba6bf279647aeafc47eb)
BibTeX
@misc{dc73da559fbe0c,
  title = {SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References — arXiv:2611.09266},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09266},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73da559fbe0c; sha256 651349b4c353d84c9c18408e77704eff75407f4dc6b0ba6bf279647aeafc47eb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09266. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scaling up visual humanoid loco-manipulation skill acquisition requires reducing the human effort needed as tasks and spatial configurations expand, particularly in demonstration collection and task-specific training design. We present SUGARv2, a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. To obtain diverse references at low cost, we adapt reusable task templates to different spatial configurations, synthesizing coordinated robot and object motions. To reduce task-specific reward design and training effort, we use reference-based imitation as a common learning objective across tasks. We first train privileged teachers to execute these references, then train visual policies through teacher distillation and reinforcement learning with the same reference-based mimic rewards, using diverse object instances and visual domain randomization to support visual generalization and sim-to-real transfer. Across five humanoid loco-manipulation tasks, SUGARv2 achieves a mean success rate of 91.0% in simulation. Deployment on a real humanoid robot further demonstrates successful sim-to-real transfer for whole-body manipulation. These results demonstrate the framework's potential for learning diverse visual humanoid loco-manipulation skills.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.09266 — 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 2026-11-09T22:38:02.192Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).