Metraipolis › archive › dc_ca9c072395cb
VAMPS: Visual and Motor Policies from Sampling-Based Planning — arXiv:2610.05331
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05331
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:49.133Z
- SHA-256 of the archived text
107eb775cde6d3e25f57c9fdf4d06cc6d76d36eb68d75c8ebe6c51f97cf1d6b0- Stable URL of this page
https://metraipolis.com/documento/dc_ca9c072395cb
How to cite
VAMPS: Visual and Motor Policies from Sampling-Based Planning — arXiv:2610.05331 — arXiv, https://arxiv.org/abs/2610.05331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca9c072395cb (Metraipolis archive dc_ca9c072395cb, sha256 107eb775cde6d3e25f57c9fdf4d06cc6d76d36eb68d75c8ebe6c51f97cf1d6b0)
BibTeX
@misc{dcca9c072395cb,
title = {VAMPS: Visual and Motor Policies from Sampling-Based Planning — arXiv:2610.05331},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05331},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca9c072395cb; sha256 107eb775cde6d3e25f57c9fdf4d06cc6d76d36eb68d75c8ebe6c51f97cf1d6b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Motor Policies from Sampling-Based Planning (VAMPS), a framework that uses Model Predictive Path Integral (MPPI) control to train reusable policies without human demonstrations. VAMPS supports two training modes. For one-step proprioceptive policies, it operates iteratively in simulation: the policy warm-starts MPPI, and the refined trajectories provide new supervision as the policy changes. A learned terminal value improves short-horizon planning, while an Implicit Q-Learning (IQL) critic guides the policy update. Iterative refinement outperforms training once on frozen MPPI data, and we transfer the learned locomotion policy to a Unitree Go2. For visuomotor policies, VAMPS operates directly from real-robot data. MPPI uses task-specific state estimates to plan and execute trajectories while recording RGB and sensor observations on a Flexiv Rizon 10S. Action Chunking with Transformers predicts action chunks, reducing the effective prediction horizon, and is trained offline on this fixed dataset. We demonstrate visuomotor pick-and-place and force-aware whiteboard erasing. In the latter task, the policy additionally observes the measured $6$-D wrench and desired normal force. These results show that VAMPS can learn policies either in simulation followed by hardware transfer or directly from autonomously collected real-robot data. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.05331 — 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 2026-10-06T05:24:05.998Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).