Metraipolis › archive › dc_f39ffb492113
PACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for Execution — arXiv:2610.07917
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07917
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:12:11.418Z
- SHA-256 of the archived text
29be9afbc741cf872cc0911ce3e7f44f49c4c3808ab33ee15e9cd4bebb335234- Stable URL of this page
https://metraipolis.com/documento/dc_f39ffb492113
How to cite
PACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for Execution — arXiv:2610.07917 — arXiv (en), https://arxiv.org/abs/2610.07917 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f39ffb492113 (Metraipolis archive dc_f39ffb492113, sha256 29be9afbc741cf872cc0911ce3e7f44f49c4c3808ab33ee15e9cd4bebb335234)
BibTeX
@misc{dcf39ffb492113,
title = {PACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for Execution — arXiv:2610.07917},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07917},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f39ffb492113; sha256 29be9afbc741cf872cc0911ce3e7f44f49c4c3808ab33ee15e9cd4bebb335234},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07917. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Demonstration-conditioned policies provide a natural interface for specifying robot behavior, yet long-horizon manipulation remains difficult when visually similar states recur across different stages or when demonstrations and executions proceed at different speeds. We identify the resulting failure mode as stage confusion and introduce Progress-Aligned Context for Execution (PACE), a stateful method that continually reinterprets a complete demonstration according to realized execution progress. PACE compresses the demonstration into ordered multimodal prompt tokens and uses training-only dual-edge attention supervision to expose its latent stage structure. During execution, an episode-local fast-weight memory causally encodes realized action-observation transitions and modulates prompt cross-attention, producing a progress-aligned context for a unified diffusion action expert without test-time stage labels or stage-specific policies. PACE improves success from 88.9% to 94.0% on LIBERO-Gen Goal Chain, from 79.1% to 83.3% on Spatial Combination, and from 33.3% to 73.3% on the two-step Block Routing tasks. Failure analysis further indicates that structured demonstration alignment and causal execution memory jointly mitigate stage confusion. 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/2610.07917 — 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 2026-10-07T12:42:33.585Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).