Metraipolis › archive › dc_26fc9e683d1e
Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation — arXiv:2608.29379
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29379
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:06:45.304Z
- SHA-256 of the archived text
919a51c0354e2146c28e4809944b48f7663ffeeb1a6c952f73405d1cc6d75e01- Stable URL of this page
https://metraipolis.com/documento/dc_26fc9e683d1e
How to cite
Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation — arXiv:2608.29379 — arXiv (en), https://arxiv.org/abs/2608.29379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26fc9e683d1e (Metraipolis archive dc_26fc9e683d1e, sha256 919a51c0354e2146c28e4809944b48f7663ffeeb1a6c952f73405d1cc6d75e01)
BibTeX
@misc{dc26fc9e683d1e,
title = {Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation — arXiv:2608.29379},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29379},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26fc9e683d1e; sha256 919a51c0354e2146c28e4809944b48f7663ffeeb1a6c952f73405d1cc6d75e01},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A language-guided robot operating in a real kitchen must do more than produce a plan that appears correct. It must also execute that plan safely in cluttered environments under imperfect perception. Large language models (LLM) can decompose instructions into action sequences, yet a language-action gap remains: a plan may appear valid linguistically while being physically infeasible under kinematic and collision constraints. We bridge this gap by formalizing the reasoning-execution boundary as a typed contract. From RGB-D observations, the system grounds perceived objects in an explicit, collision-aware scene model and constrains language-level decisions through schema-validated tool calls defined by the Model Context Protocol (MCP), rejecting malformed commands before they reach the robot. Each validated call is deterministically grounded in a MoveIt Task Constructor pipeline, where candidate motions are evaluated against the reconstructed planning scene in a verify-then-act step. Only trajectories that pass both kinematic and collision checks are sent to the robot. On a physical UFactory 850, the method achieves up to 80% success across ten trials per task on pouring tasks involving liquids, granular media, and discrete solids. It achieves 90% success on a grasp-and-place task using the same planning, protocol, and verification stack. Although a scripted policy slightly outperforms our method on the easiest task, its success rate falls to 10% on the hardest, compared with 60% for our method. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.29379 — 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 2026-10-17T09:58:57.771Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).