Metraipolis › archive › dc_cbcc2822d405
PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing — arXiv:2609.31717
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31717
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:50:31.329Z
- SHA-256 of the archived text
0c8245d801f758398093940a6a3843cd8ac4f0472e88bb9ed9f65277a5f5b270- Stable URL of this page
https://metraipolis.com/documento/dc_cbcc2822d405
How to cite
PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing — arXiv:2609.31717 — arXiv (en), https://arxiv.org/abs/2609.31717 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbcc2822d405 (Metraipolis archive dc_cbcc2822d405, sha256 0c8245d801f758398093940a6a3843cd8ac4f0472e88bb9ed9f65277a5f5b270)
BibTeX
@misc{dccbcc2822d405,
title = {PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing — arXiv:2609.31717},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31717},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbcc2822d405; sha256 0c8245d801f758398093940a6a3843cd8ac4f0472e88bb9ed9f65277a5f5b270},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31717. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems rely on conventional perspective cameras with limited fields of view, often missing global scene context and leading to unreliable manipulation under visual occlusions, distractors, and unseen environments. In this work, we propose PanoFuse, a panorama-enhanced VLA framework that complements local manipulation observations with global panoramic perception. PanoFuse introduces a dedicated panoramic branch that leverages a pretrained panoramic foundation model to extract complementary semantic and geometric representations from omnidirectional observations. Rather than directly mixing these heterogeneous features, we introduce Decoupled Semantic-Geometric Routing (DSGR), which maintains semantic and geometric representations as separate context streams and selectively routes both to downstream state and action representations through structured block-wise attention. This design provides the action expert with global spatial context while preserving task-relevant semantic information from the pretrained VLA backbone. We further develop a synchronized data collection pipeline and construct a new real-world manipulation dataset containing panoramic RGB observations, wrist-view images, language instructions, robot states, and actions. Across seven evaluation settings, PanoFuse achieves an average success rate of 52.9%, outperforming the evaluated baselines and achieving consistent gains under novel-object, unseen-background, and distractor-rich settings. Code and data will be released publicly at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.31717 — 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 2026-10-07T23:29:26.894Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).