Metraipolis › archive › dc_3847c197fa05
Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation — arXiv:2609.18243
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18243
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:07:57.125Z
- SHA-256 of the archived text
97a9e94367613fcf7090110155520efc191b9263bbd3f08954156b1118b54ef9- Stable URL of this page
https://metraipolis.com/documento/dc_3847c197fa05
How to cite
Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation — arXiv:2609.18243 — arXiv (en), https://arxiv.org/abs/2609.18243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3847c197fa05 (Metraipolis archive dc_3847c197fa05, sha256 97a9e94367613fcf7090110155520efc191b9263bbd3f08954156b1118b54ef9)
BibTeX
@misc{dc3847c197fa05,
title = {Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation — arXiv:2609.18243},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18243},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3847c197fa05; sha256 97a9e94367613fcf7090110155520efc191b9263bbd3f08954156b1118b54ef9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action models and World-Action Models have advanced language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Human manipulation combines semantic understanding of task-relevant objects with spatial feedback that guides hand motion relative to objects and their surroundings. Inspired by this, we introduce a metric interaction framework that models object-level and scene-level interactions in physical Cartesian space at a shared metric scale. At the object level, Interaction-Centric Tokens (ICTs) explicitly represent end-effector pose trajectories relative to manipulated objects and are jointly denoised with actions, providing physically grounded interaction supervision. At the scene level, the Metric Action Interaction Field (MAIF) uses action and ICT queries to attend to metric scene point-cloud features and learns geometry-conditioned action corrections. Through two-stage adaptation, our framework improves diverse VLA and WAM baselines with a small number of additional parameters and training steps. Experiments demonstrate average success-rate gains of 0.80 and 3.59 percentage points on LIBERO and RoboTwin 2.0, respectively, alongside gains of 6.80 percentage points on real-world tasks and 7.45 percentage points on their out-of-distribution variants. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.18243 — 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 2026-10-15T14:08:19.240Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).