Metraipolis › archive › dc_9154fe69a463
ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph — arXiv:2609.16331
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16331
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:30:23.227Z
- SHA-256 of the archived text
4ac20f8b5e0cc765a1ee7ca4382c3855b3390e211ce77480e8fe9c7045404ed2- Stable URL of this page
https://metraipolis.com/documento/dc_9154fe69a463
How to cite
ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph — arXiv:2609.16331 — arXiv (en), https://arxiv.org/abs/2609.16331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9154fe69a463 (Metraipolis archive dc_9154fe69a463, sha256 4ac20f8b5e0cc765a1ee7ca4382c3855b3390e211ce77480e8fe9c7045404ed2)
BibTeX
@misc{dc9154fe69a463,
title = {ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph — arXiv:2609.16331},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16331},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9154fe69a463; sha256 4ac20f8b5e0cc765a1ee7ca4382c3855b3390e211ce77480e8fe9c7045404ed2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Adapting robotic manipulation to new objects and tasks often requires additional demonstrations or manual engineering. Reusable manipulation skills can reduce this effort, but adapting these skills to new scenes remains challenging. We present ManiSkillFormer, a framework for demonstration-free and compositional manipulation that connects perception and action through explicit geometric contracts. Building on reusable skill schemas, LLM agents generate contracts specifying the geometry primitives required by each skill, together with corresponding motion templates for semantic objects and task contexts. These contracts guide a perception module to ground task-relevant 3D geometry from observations, which is then used to instantiate reusable motion templates in a skill library. We evaluate ManiSkillFormer on a dual-arm robot across demonstration-free pick-and-place with 30 instances from 8 object categories, functional manipulation including unscrewing, pouring, pressing, and folding, and three long-horizon tasks. ManiSkillFormer achieves an average success rate of 88.97% for pick-and-place, 75.00% for functional manipulation, and completion rates of 50--80% across the long-horizon tasks, outperforming the evaluated baselines and two ablated pipelines. These results demonstrate the potential of explicit geometric contracts to support skill reuse and composition across objects and tasks without per-object policy fine-tuning or additional robot demonstrations. The project website is at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-16 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.16331 — 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 2026-10-15T21:30:17.311Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).