Metraipolis › archive › dc_bd3b9deb2dcc
Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning — arXiv:2610.19617
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19617
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:43.323Z
- SHA-256 of the archived text
cbed3e8ce7e2f616fa051284fcf4dc78167e06c5f5101113e78b44fe2eb949a6- Stable URL of this page
https://metraipolis.com/documento/dc_bd3b9deb2dcc
How to cite
Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning — arXiv:2610.19617 — arXiv (en), https://arxiv.org/abs/2610.19617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd3b9deb2dcc (Metraipolis archive dc_bd3b9deb2dcc, sha256 cbed3e8ce7e2f616fa051284fcf4dc78167e06c5f5101113e78b44fe2eb949a6)
BibTeX
@misc{dcbd3b9deb2dcc,
title = {Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning — arXiv:2610.19617},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19617},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd3b9deb2dcc; sha256 cbed3e8ce7e2f616fa051284fcf4dc78167e06c5f5101113e78b44fe2eb949a6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Instruction-Conditioned Motion Control (ICMC) separates parameter specification, instruction generation, and code synthesis for language-driven robot control, making execution outcomes traceable to instructions and programs. We compare one-shot generation with ICMC under o1 and o4-mini on cube pick-and-place and letter-reshaping tasks for a UR5e arm in MuJoCo. We then train an open-weight instruction policy by GRPO through a frozen code generator on cube placement onto two- and five-cube letter layouts, averaging the rewards of five programs per instruction. The logged positive-reward rate rose from 31.6% to 35.3% (253/800 to 282/800) between the first and last five training steps. A log audit identifies positive binary labels associated with geometric-failure messages: at least 19 in that run, 18 in the dense-reward run, and 5 in the run with one program per instruction. In one case, all five rewards were 1.0 while the log reports a 0.9515 m miss against a 0.05 m tolerance; the verdict came from the program's own output stream. We distinguish logged reward rates from independently verified task success and report descriptive results for each configuration's single training trajectory. We introduce an independent evaluation protocol that checks task completion against fixed specifications, separating robot control from success assessment to support reproducible evaluation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19617 — 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 2026-10-15T19:35:48.352Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).