Metraipolis › archive › dc_51b0849fbdfa
DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation — arXiv:2609.25631
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25631
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:43:27.359Z
- SHA-256 of the archived text
f24bc10f271128022421819a23a80be718c4b7e60f5cfeb1e11adeb08fb18ba6- Stable URL of this page
https://metraipolis.com/documento/dc_51b0849fbdfa
How to cite
DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation — arXiv:2609.25631 — arXiv (en), https://arxiv.org/abs/2609.25631 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_51b0849fbdfa (Metraipolis archive dc_51b0849fbdfa, sha256 f24bc10f271128022421819a23a80be718c4b7e60f5cfeb1e11adeb08fb18ba6)
BibTeX
@misc{dc51b0849fbdfa,
title = {DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation — arXiv:2609.25631},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25631},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_51b0849fbdfa; sha256 f24bc10f271128022421819a23a80be718c4b7e60f5cfeb1e11adeb08fb18ba6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25631. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dynamic object manipulation is essential for robots operating in real-world environments, yet methods for generating high-quality demonstrations remain limited. Methods designed for static tasks do not readily transfer to dynamic settings. Among dynamic demonstration generators, planning-based methods can fail near contact, while DOMINO-style replay simplifies dynamic interactions and may limit the experience available for policy learning. We present DynaForge, a planning-guided framework that learns residual corrections for dynamic manipulation demonstration generation. DynaForge combines low-frequency global planning with high-frequency object-centric inverse kinematics across task phases, and applies a residual policy to correct actions during dynamic interaction. An implicit curriculum groups rollouts under matched conditions and selects mixed-success groups, focusing residual reinforcement learning on the evolving competence frontier. On Can and Bottle, it uses 0.73x as many optimizer steps as vanilla GRPO at the same nominal environment-step budget, with higher observed final success rates. Across nine simulation tasks, DynaForge increases mean demonstration-generation success from 41.30% of the planning prior to 78.37%. With 800 demonstrations per task, DP3 policies trained on DynaForge data achieve 49.11% mean success, compared with 7.07% for DOMINO data. On three real-world dynamic tasks, DynaForge-trained policies achieve 30-60% success, compared with 0-10% for DOMINO-trained policies, showing the ability of DynaForge for sim-to-real transfer. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.25631 — 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 2026-10-08T15:56:53.442Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).