Metraipolis › archive › dc_e54ff951d256
Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation — arXiv:2611.04477
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04477
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:05:12.431Z
- SHA-256 of the archived text
286d1e5d2d5a5909628b63ae723a67ed36a538a0a92426290629b94fe62492e0- Stable URL of this page
https://metraipolis.com/documento/dc_e54ff951d256
How to cite
Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation — arXiv:2611.04477 — arXiv (en), https://arxiv.org/abs/2611.04477 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e54ff951d256 (Metraipolis archive dc_e54ff951d256, sha256 286d1e5d2d5a5909628b63ae723a67ed36a538a0a92426290629b94fe62492e0)
BibTeX
@misc{dce54ff951d256,
title = {Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation — arXiv:2611.04477},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04477},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e54ff951d256; sha256 286d1e5d2d5a5909628b63ae723a67ed36a538a0a92426290629b94fe62492e0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04477. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion-based policies have achieved strong performance on single-task robotic manipulation. However, a single model trained jointly on multiple tasks consistently underperforms the per-task specialists trained on the same demonstrations. We focus on two challenges. First, the convolutional encoders commonly used in diffusion-based policies produce visual conditions that are not discriminative enough. Second, gradients from incompatible action modes update the shared denoiser's dense parameters along the same directions, causing destructive interference during joint training. To address both, we propose SR-DP (Spectrally Routed Diffusion Policy). A frozen VGGT encoder with a spatial-compression adapter produces compact multi-scale semantic-geometric tokens, a task-discriminative visual condition for tasks that share a workspace. We first train the denoiser as a standard diffusion policy, then decompose selected linear layers by SVD into a frozen basis of orthogonal rank-one experts, adapted through spectral routing and Householder input rotations. On six RoboTwin tasks, SR-DP averages a 68.4% success rate, surpassing multi-task VO-DP by 21.8 points and the strongest per-task baseline by 3.8 points. On four real-world bimanual tasks, Stage 2 reaches a 43.0% average success rate and improves over Stage 1 by 19.0 points. 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/2611.04477 — 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 2026-11-04T18:39:52.402Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).