Metraipolis › archive › dc_af6ec85fc647

RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution — arXiv:2608.15924

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15924
License (as archived)
CC0-1.0
Archived
2026-10-18T23:05:55.575Z
SHA-256 of the archived text
090976f5e2e2a52420f80af4d018aaf10846c68653baa8e6ac7c19fb0099453b
Stable URL of this page
https://metraipolis.com/documento/dc_af6ec85fc647

How to cite

RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution — arXiv:2608.15924 — arXiv (en), https://arxiv.org/abs/2608.15924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af6ec85fc647 (Metraipolis archive dc_af6ec85fc647, sha256 090976f5e2e2a52420f80af4d018aaf10846c68653baa8e6ac7c19fb0099453b)
BibTeX
@misc{dcaf6ec85fc647,
  title = {RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution — arXiv:2608.15924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af6ec85fc647; sha256 090976f5e2e2a52420f80af4d018aaf10846c68653baa8e6ac7c19fb0099453b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cloud-side inference gives imitation-learning policies access to greater computational resources, but communication and computation delays can degrade control performance. To compensate for these delays, we propose RAPAC-DP, a response-aligned pending-action compensation framework designed for both diffusion- and flow-based action generators. RAPAC-DP encodes the actions already scheduled for execution before the cloud response arrives into a pending-action sequence that serves as the conditioning input to a parameter-efficient compensation pathway. When delay effects are negligible, bypassing this pathway exactly recovers the frozen base policy. For training, RAPAC-DP constructs delay-conditioned samples from delay-free demonstrations, requiring neither explicit system dynamics nor additional delayed demonstrations. At the largest fixed delay tested on Kinetix, RAPAC-DP retained 81.4% of its overall delay-free performance. At the largest fixed delay tested on each RoboMimic task, it achieved a mean success rate of 0.633 across the three tasks. These results demonstrate the effectiveness of pending-action compensation for cloud-deployed imitation-learning policies.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.15924 — 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 2026-10-18T23:01:50.368Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).