Metraipolis › archive › dc_19c0631ee6ed
SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping — arXiv:2611.02794
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02794
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:41:16.443Z
- SHA-256 of the archived text
8e417e87e88de2e6a534abb29c34c439b8a3cdd737c0ba9a9f83b7c00699f952- Stable URL of this page
https://metraipolis.com/documento/dc_19c0631ee6ed
How to cite
SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping — arXiv:2611.02794 — arXiv (en), https://arxiv.org/abs/2611.02794 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19c0631ee6ed (Metraipolis archive dc_19c0631ee6ed, sha256 8e417e87e88de2e6a534abb29c34c439b8a3cdd737c0ba9a9f83b7c00699f952)
BibTeX
@misc{dc19c0631ee6ed,
title = {SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping — arXiv:2611.02794},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02794},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19c0631ee6ed; sha256 8e417e87e88de2e6a534abb29c34c439b8a3cdd737c0ba9a9f83b7c00699f952},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02794. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robust multimodal perception for soft robotic grasping is challenged by modality-dependent noise, semantic ambiguity, and limited coordinated multisensory data. We introduce Soma, a dataset containing 100 objects, 1,000 continuous grasping trajectories, and 74,914 multimodal samples grouped by software acquisition cycle, spanning remote RGB, hand RGB, depth, tactile, IMU, and structured text observations. We also collect Soma-Success, an independent grasp-outcome dataset with 1,000 trials (998 retained after quality control), to evaluate frozen-encoder transfer for post-hoc grasp outcome classification and early grasp success prediction. Built on Soma, SomaAlign learns multimodal representations in three stages: masked reconstruction estimates relative modality reliability; reliability-aware contrastive alignment uses pair-specific adaptive temperatures to adjust alignment sharpness; and conflict-aware semantic constraints improve intra-sample cross-modal consistency while preserving global feature geometry. SomaAlign achieves an average Recall@10 of 90.66% across 30 directed cross-modal retrieval tasks. The learned representations also support physical attribute recognition, multimodal question answering, cross-modal generation, and cross-dataset transfer to grasp outcome prediction. On Soma-Success, frozen SomaAlign encoders with lightweight probes achieve 94.59% post-hoc classification accuracy and 84.07% early prediction accuracy. Together, Soma, Soma-Success, and SomaAlign provide a data and representation-learning foundation for robust and transferable multimodal perception in soft robotic manipulation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02794 — 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 2026-11-03T18:12:54.784Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).