Metraipolis › archive › dc_e68ed211da0f
MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies — arXiv:2610.22193
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22193
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:40:10.185Z
- SHA-256 of the archived text
547e8c3fe32f9f8954898e5d724edcaf9c429d11f7dc26bcb86f29c4ab49d0f9- Stable URL of this page
https://metraipolis.com/documento/dc_e68ed211da0f
How to cite
MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies — arXiv:2610.22193 — arXiv (en), https://arxiv.org/abs/2610.22193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e68ed211da0f (Metraipolis archive dc_e68ed211da0f, sha256 547e8c3fe32f9f8954898e5d724edcaf9c429d11f7dc26bcb86f29c4ab49d0f9)
BibTeX
@misc{dce68ed211da0f,
title = {MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies — arXiv:2610.22193},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22193},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e68ed211da0f; sha256 547e8c3fe32f9f8954898e5d724edcaf9c429d11f7dc26bcb86f29c4ab49d0f9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally capture such multimodal behaviors, yet which mode is executed is left to random sampling and cannot be actively controlled. We propose Mode-Oriented Source Shaping (MOSS), which turns mode selection into an explicit choice of where generation starts. We first reveal, both empirically and theoretically, that deterministic flow transport induces mode-dependent structure in the source space. Under ideal deterministic ODE transport, distinct behavioral modes have distinct source-space preimages, while practical approximation errors can blur their boundaries due to imbalanced data, limited model capacity, and few inference steps. Motivated by this source-space structure, MOSS constructs semantically aligned mode-specific Gaussian sources that encode mode identity in the initial noise. A modality-strength estimator predicts the local degree of multimodality, which adaptively controls the geometry of the mode-specific sources. It contracts them toward a shared Gaussian where behaviors are similar and separates them near behavioral branching points. During deployment, the desired behavior is selected at inference simply by sampling from the corresponding component. Across 6 simulated and 3 real-world manipulation tasks, MOSS steers to the target mode up to 100% of the time with high task success, recovers minority modes at over 90% guidance rate under a 10:90 imbalance dataset, and surpasses mode-conditioned flow policy by 43.3 points of guidance rate on real robots. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.22193 — 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 2026-10-16T08:52:17.704Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).