Metraipolis › archive › dc_5d243bad0855
Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning — arXiv:2610.39451
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39451
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:25:06.874Z
- SHA-256 of the archived text
63e4f2e07f979840ba91fc04ebcb79ee9bdd5cb98f55efa8efbcffa884c0806f- Stable URL of this page
https://metraipolis.com/documento/dc_5d243bad0855
How to cite
Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning — arXiv:2610.39451 — arXiv (en), https://arxiv.org/abs/2610.39451 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d243bad0855 (Metraipolis archive dc_5d243bad0855, sha256 63e4f2e07f979840ba91fc04ebcb79ee9bdd5cb98f55efa8efbcffa884c0806f)
BibTeX
@misc{dc5d243bad0855,
title = {Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning — arXiv:2610.39451},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39451},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d243bad0855; sha256 63e4f2e07f979840ba91fc04ebcb79ee9bdd5cb98f55efa8efbcffa884c0806f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39451. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Imitation learning has become a widely adopted approach for vision-based robot policies, owing to its conceptual simplicity, scalability, and ability to leverage large-scale datasets. As these policies have grown more capable, action chunking has become their standard interface. At each decision step the policy outputs several future actions at once. Backbones from diffusion policies to large vision-language-action models all share it. Whatever backbone produces the chunk, its temporal structure is learned only implicitly. The commanded trajectory is therefore jerky both within a chunk and between successive chunks. On real hardware this appears as visible vibration and as repeated saturation of the follower's velocity limit. We address this issue by incorporating a movement-primitive-based trajectory representation into action chunking. Specifically, a trajectory segment is represented as a linear combination of smooth basis functions, yielding smooth trajectories by construction while leaving the policy architecture, training objective, and inference procedure unchanged. The same representation also yields a closed-form, inference-time correction for the second source of jerk. We condition the predicted coefficients so that the new chunk passes through a via-point at the previous chunk's last commanded action. This correction needs no retraining and, unlike asynchronous Real-Time Chunking, applies to policies queried in one shot. We instantiate it on a one-shot (ACT) and an iterative (DiT) backbone and evaluate in simulation and on a real bimanual ALOHA platform. The representation lowers within-chunk jerk by an order of magnitude on the one-shot backbone and by 2.4 times on the iterative one, with task success statistically non-inferior. The conditioning then removes 73-84% of the boundary discontinuity, at negligible per-step cost. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.39451 — 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 2026-11-01T02:12:44.168Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).