Metraipolis › archive › dc_69a661c0d3cb

MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning — arXiv:2609.24995

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24995
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:40.074Z
SHA-256 of the archived text
8630c42ec85d2d4b9f907b6f25104ab02bbdfc05008e7fe0d2df3be3231f3aa1
Stable URL of this page
https://metraipolis.com/documento/dc_69a661c0d3cb

How to cite

MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning — arXiv:2609.24995 — arXiv (en), https://arxiv.org/abs/2609.24995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69a661c0d3cb (Metraipolis archive dc_69a661c0d3cb, sha256 8630c42ec85d2d4b9f907b6f25104ab02bbdfc05008e7fe0d2df3be3231f3aa1)
BibTeX
@misc{dc69a661c0d3cb,
  title = {MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning — arXiv:2609.24995},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24995},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69a661c0d3cb; sha256 8630c42ec85d2d4b9f907b6f25104ab02bbdfc05008e7fe0d2df3be3231f3aa1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding natural human instructions is crucial for deploying robots in human-centric environments. We study multimodal instruction grounding, where language and gesture provide complementary but uncertain cues. We present MIGU, a modular framework that combines semantic and geometric evidence into a unified grounding belief and connects it to manipulation planning. MIGU constructs a 3D geometric likelihood by propagating viewing-direction and depth uncertainty through eye-finger geometry while accounting for hand-direction estimation error. A vision-language model (VLM) provides semantic priors over candidate objects and regions, which are combined with the geometric likelihood through Bayes-inspired fusion. The resulting belief supports behavior planning to either proceed directly to downstream planning or request clarification. Grounded targets then define goals for mobile manipulation and tabletop task-and-motion planning. On a real-world benchmark, MIGU outperforms all evaluated baselines, while ablations support the benefit of explicit multimodal uncertainty modeling. Project website: this http URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.24995 — 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 2026-10-09T21:59:59.784Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).