Metraipolis › archive › dc_42ca4f59a080

Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation — arXiv:2610.41320

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41320
License (as archived): CC0-1.0
Archived: 2026-11-02T05:05:37.873Z
SHA-256 of the archived text: f33dca504acdc41f8d023f846a819cdff4f6cc4f2169387a968bc12fc00a8fa1
Stable URL of this page: https://metraipolis.com/documento/dc_42ca4f59a080

How to cite

Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation — arXiv:2610.41320 — arXiv (en), https://arxiv.org/abs/2610.41320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_42ca4f59a080 (Metraipolis archive dc_42ca4f59a080, sha256 f33dca504acdc41f8d023f846a819cdff4f6cc4f2169387a968bc12fc00a8fa1)

BibTeX

@misc{dc42ca4f59a080,
  title = {Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation — arXiv:2610.41320},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41320},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_42ca4f59a080; sha256 f33dca504acdc41f8d023f846a819cdff4f6cc4f2169387a968bc12fc00a8fa1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent multimodal foundation models exhibit strong perception, reasoning, and in-context learning capabilities, but translating these capabilities into physical action remains challenging. Through real-world experiments across diverse manipulation tasks, we find that ChatGPT-6-Astra, a state-of-the-art general-purpose reasoner, can serve as a physically actionable, context-responsive manipulation policy, demonstrating effective fine manipulation and spatial reasoning. Building on these findings, we introduce LEXP, a harness for learning from physical experience through context-space adaptation. LEXP combines task-level planning with an experience module that interprets execution evidence, extracts and retains lessons with applicability conditions, and reuses relevant lessons to generate contextual feedback for subsequent actions. Model weights and the action interface remain fixed throughout. Across 12 real-world manipulation tasks, LEXP achieves $23/36$ successful trials (63.9\%), compared with $19/36$ (52.8\%) with memory alone and $2/36$ (5.6\%) for vanilla Astra. On three tasks, bread transfer, sort trash and toiletries, and retrieve drawer, removing planning reduces success from $7/9$ to $4/9$, while removing retained experience reduces it to $3/9$. Execution traces illustrate feedback-guided corrections and cross-episode reuse of an inspection strategy. Execution analyses illustrate how task structure and experience-derived feedback guide task progression, action correction, and experience reuse. These results support context-space adaptation as a practical mechanism for turning physical interaction into reusable guidance for robotic manipulation.

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/2610.41320 — 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 2026-11-02T04:49:28.196Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).