Metraipolis › archive › dc_5d794acdf8a9
Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusion — arXiv:2609.33546
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33546
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T00:17:10.296Z
- SHA-256 of the archived text
290c1f04c8a0b65ad92e3956495e67bf458f86b77848dc94795b3ac43c4f6844- Stable URL of this page
https://metraipolis.com/documento/dc_5d794acdf8a9
How to cite
Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusion — arXiv:2609.33546 — arXiv (en), https://arxiv.org/abs/2609.33546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d794acdf8a9 (Metraipolis archive dc_5d794acdf8a9, sha256 290c1f04c8a0b65ad92e3956495e67bf458f86b77848dc94795b3ac43c4f6844)
BibTeX
@misc{dc5d794acdf8a9,
title = {Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusion — arXiv:2609.33546},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33546},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d794acdf8a9; sha256 290c1f04c8a0b65ad92e3956495e67bf458f86b77848dc94795b3ac43c4f6844},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Current grasp diffusion models provide rich priors for generation, yet their object-centric approach can violate the kinematic and collision constraints imposed by the embodiment and the environment. Existing embodiment-aware methods primarily perform local corrections around generated grasps through gradient guidance or optimization, making it difficult to recover from fundamentally infeasible modes. We present Steer2Grasp, a training-free, embodiment-agnostic framework for inference-time grasp steering that adapts a frozen Cartesian grasp diffusion model using deployment-specific rewards. Through Feynman-Kac (FK) inspired particle reweighting and resampling, the method reallocates population mass from infeasible to high-reward grasp modes, enabling population-level mode transitions without modifying the pretrained diffusion model or requiring differentiable constraints. The framework enables a unified treatment for single and dual arm grasping through reachability and collision aware rewards, followed by gradient free gripper level local refinement. Across diverse objects, robot embodiments, and constrained environments, our method substantially improves feasible grasp generation while maintaining proximity to the underlying grasp prior. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.33546 — 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 2026-10-07T23:52:16.481Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).