Metraipolis › archive › dc_4ac4c69cee89
Expert-Play Contouring Control: Faster-than-Demonstration Planning from Slow Expert and Fast Play — arXiv:2609.22798
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22798
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:23:35.343Z
- SHA-256 of the archived text
a1eedb646736360d23bcbb9461f3b24eed44775829eabfb34a9cce99dc0fa20f- Stable URL of this page
https://metraipolis.com/documento/dc_4ac4c69cee89
How to cite
Expert-Play Contouring Control: Faster-than-Demonstration Planning from Slow Expert and Fast Play — arXiv:2609.22798 — arXiv (en), https://arxiv.org/abs/2609.22798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ac4c69cee89 (Metraipolis archive dc_4ac4c69cee89, sha256 a1eedb646736360d23bcbb9461f3b24eed44775829eabfb34a9cce99dc0fa20f)
BibTeX
@misc{dc4ac4c69cee89,
title = {Expert-Play Contouring Control: Faster-than-Demonstration Planning from Slow Expert and Fast Play — arXiv:2609.22798},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22798},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ac4c69cee89; sha256 a1eedb646736360d23bcbb9461f3b24eed44775829eabfb34a9cce99dc0fa20f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Expert demonstrations often specify what a robot should do, but not how fast it can do it. Imitation Learning (IL) inherits demonstration timing, while directly accelerating the learned motion can fail when faster execution changes the robot-object dynamics. We study faster-than-demonstration execution as a dynamics-aware control problem and introduce Expert-Play Contouring Control (EPCC), which combines slow expert demonstrations with fast, non-expert play. Expert demonstrations train a latent trajectory generator whose predictions are reparameterized into a time-independent contour of successful task progression, while play trains a world model (WM) of fast-action outcomes. At deployment, our proposed planner uses the WM to optimize actions that makes maximize progress along the expert-derived contour while penalizing deviation from the intended task evolution. Averaged across three visuomotor manipulation tasks, EPCC achieves a $2.0\times$ the throughput of the IL baseline, including $2.2\times$ that of the throughput of the strongest acceleration baseline on a task with interaction-sensitive object dynamics. Our analysis shows that the gains concentrate where faster execution changes robot-object evolution. Together, our results highlight a simple yet effective principle: demonstrations provide task intent, while play data provides the dynamic coverage needed to execute that intent faster. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.22798 — 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 2026-10-09T21:59:59.475Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).