Metraipolis › archive › dc_71bad036ee9a

Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer — arXiv:2609.22521

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22521
License (as archived)
CC0-1.0
Archived
2026-10-09T22:21:25.336Z
SHA-256 of the archived text
1ce00eb1206f902306946abbf7c2d7e31cba941610b37d8da1488bc0a3e43ef1
Stable URL of this page
https://metraipolis.com/documento/dc_71bad036ee9a

How to cite

Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer — arXiv:2609.22521 — arXiv (en), https://arxiv.org/abs/2609.22521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71bad036ee9a (Metraipolis archive dc_71bad036ee9a, sha256 1ce00eb1206f902306946abbf7c2d7e31cba941610b37d8da1488bc0a3e43ef1)
BibTeX
@misc{dc71bad036ee9a,
  title = {Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer — arXiv:2609.22521},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22521},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71bad036ee9a; sha256 1ce00eb1206f902306946abbf7c2d7e31cba941610b37d8da1488bc0a3e43ef1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The performance of learned robot visuomotor policies depends heavily on the size and quality of their training data, yet collecting high-quality demonstrations remains costly for robots in the real world. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage directly. Cross-embodiment transfer, reusing experience from other embodiments to improve learning on a target embodiment, is therefore crucial for scaling robot learning beyond per-robot data collection. In this work, we find that efficient transfer can be achieved by learning from what is shared across embodiments, the visual dynamics of how the world responds to motion, and by effectively exploiting the scarce target-embodiment data at test time. The proposed framework, called Latent Policy Steering (LPS), implements an embodiment-agnostic pretraining phase, which trains an image-based World Model (WM) with optical flow across diverse embodiments. The resulting WM is finetuned on the target embodiment with robot actions. It then steers the base policy toward better actions by searching in the WM's latent space for plans that stay close to the finetuning data. LPS is a policy-agnostic framework: it can flexibly accommodate different policies without having to retrain them. In Robomimic and real-world evaluations, LPS improves the average performance of Diffusion Policy relatively by 16% and 62%, and Pi0.5 by 8% and 14%, with only 50 demonstrations on an unseen target embodiment.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.22521 — 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 2026-10-09T21:59:59.430Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).