Metraipolis › archive › dc_000226de2aec

BooST: Bridging Semantics and Motions for Efficient Skill Transfer — arXiv:2608.10600

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10600
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:49.239Z
SHA-256 of the archived text
660e30a258ceacd1347a9a29e0206e0b7efd647042b05ebb0294c9d2f37f4424
Stable URL of this page
https://metraipolis.com/documento/dc_000226de2aec

How to cite

BooST: Bridging Semantics and Motions for Efficient Skill Transfer — arXiv:2608.10600 — arXiv (en), https://arxiv.org/abs/2608.10600 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_000226de2aec (Metraipolis archive dc_000226de2aec, sha256 660e30a258ceacd1347a9a29e0206e0b7efd647042b05ebb0294c9d2f37f4424)
BibTeX
@misc{dc000226de2aec,
  title = {BooST: Bridging Semantics and Motions for Efficient Skill Transfer — arXiv:2608.10600},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10600},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_000226de2aec; sha256 660e30a258ceacd1347a9a29e0206e0b7efd647042b05ebb0294c9d2f37f4424},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10600. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Skill abstraction---the process of learning reusable and temporally extended behaviors---has emerged as a key paradigm for improving sample efficiency and generalization in robot learning. For efficient skill transfer to real robots, learned skills must generalize across tasks and domains, remain robust to visual and dynamic perturbations, and be efficient enough for practical deployment. However, existing methods typically satisfy only a subset of these properties, as they capture either high-level semantic intent (what) or low-level motion dynamics (how). This incomplete skill transfer yields weak priors for policy learning, thereby demanding substantial in-domain data for downstream adaptation. To address these challenges, we introduce BooST, a two-stage framework that explicitly bridges semantics and motions to satisfy all three desiderata. BooST first leverages a cross-modal VQ-VAE to capture both semantic intent and motion dynamics, yielding a unified skill representation. It then distills this representation into a lightweight policy for efficient downstream adaptation to new tasks. Extensive experiments across simulation and real-robot settings demonstrate that BooST achieves superior few-shot adaptation, cross-domain skill transfer, and robustness to dynamic visual distractors, while maintaining a lightweight yet expressive design suitable for real-world deployment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10600 — 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 2026-10-19T06:11:45.144Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).