Metraipolis › archive › dc_b6463eeae4cd

Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints — arXiv:2609.09597

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09597
License (as archived): CC0-1.0
Archived: 2026-10-16T07:25:57.790Z
SHA-256 of the archived text: 455af25da0f478fdfd91f4496c3dbc8451ce7f6358211276f890387ff85b84ec
Stable URL of this page: https://metraipolis.com/documento/dc_b6463eeae4cd

How to cite

Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints — arXiv:2609.09597 — arXiv (en), https://arxiv.org/abs/2609.09597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6463eeae4cd (Metraipolis archive dc_b6463eeae4cd, sha256 455af25da0f478fdfd91f4496c3dbc8451ce7f6358211276f890387ff85b84ec)

BibTeX

@misc{dcb6463eeae4cd,
  title = {Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints — arXiv:2609.09597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6463eeae4cd; sha256 455af25da0f478fdfd91f4496c3dbc8451ce7f6358211276f890387ff85b84ec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate tactile forecasts need not improve force-constrained control. We study a 652,157-parameter action-conditioned visuotactile world model with matched behavior cloning, policy learning in imagination, independent reactive implicit Q-learning, and model-assisted force feedback. A fixed protocol executes 34 policies on 120 fresh MuJoCo environments spanning geometry and physical-parameter shifts, plus 324 independently replayed action branches on 12 additional ID environments. Visuotactile dynamics reduce force action-effect MAE from 0.413 N for persistence to 0.338 N. Model-assisted feedback raises ID force-budgeted success from 73.3% to 93.3%, with paired difference +20.0 [+6.7,+33.4] percentage points (95% CI), with the difference occurring during scripted lowering. Its pooled difference is +3.9 [-4.5,+11.7] points. Imagined RL achieves 11.9% pooled joint success versus 25.0% for reactive IQL. An empirical tactile-residual stress test adds 330 executions. The evidence concerns rigid-box lifting after a common approach, without physical-robot transfer or a closed-loop safety guarantee.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09597 — 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 2026-10-16T07:00:16.329Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).