Metraipolis › archive › dc_fb3fa430e64a
Coupled State-Space Modelling, Control, and Policy Distillation for Hybrid Rigid-Pneumatic Manipulators — arXiv:2609.29424
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29424
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T07:16:59.033Z
- SHA-256 of the archived text
85555922a87beff30cc42b9c61414f824817d5e389f0bc1983f80ea10b215724- Stable URL of this page
https://metraipolis.com/documento/dc_fb3fa430e64a
How to cite
Coupled State-Space Modelling, Control, and Policy Distillation for Hybrid Rigid-Pneumatic Manipulators — arXiv:2609.29424 — arXiv (en), https://arxiv.org/abs/2609.29424 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb3fa430e64a (Metraipolis archive dc_fb3fa430e64a, sha256 85555922a87beff30cc42b9c61414f824817d5e389f0bc1983f80ea10b215724)
BibTeX
@misc{dcfb3fa430e64a,
title = {Coupled State-Space Modelling, Control, and Policy Distillation for Hybrid Rigid-Pneumatic Manipulators — arXiv:2609.29424},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29424},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb3fa430e64a; sha256 85555922a87beff30cc42b9c61414f824817d5e389f0bc1983f80ea10b215724},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29424. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hybrid manipulators combine motorized rigid joints with pressure-actuated origami segments. Published arms of this kind are controlled with decoupled per-DOF loops, and the cost of this approximation has not been quantified, because the coupled model needed to measure it has not been built. This paper derives such a model for a chain of $N$ alternating revolute joints and Kresling origami segments, including pneumatic chamber dynamics and crease hysteresis. Using the model, we measure the coupling directly and show that its strength varies joint by joint, and that decoupled control loses precisely on the strongly coupled joints while remaining competitive on the one nearly decoupled joint. Coupled model-based controllers track $2.5\times$ tighter than a decoupled PID baseline at lower torque. However, the model predictive controller (MPC) is too slow for real time, and model-free reinforcement learning stalls far below acceptable success rates on a strict settling metric. We therefore distill the MPC into a small neural policy with behavior cloning and DAgger. The distilled policy settles 93-94$\%$ of goals with zero collisions, within a few points of its teacher, and runs inside the 5 ms control step where the MPC does not. Where the teacher itself fails, we trace the failure to a limit cycle with the bellows' lightly damped mode, and we remove it by selecting goal postures holdable at low pressure. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.29424 — 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 2026-10-08T06:38:53.815Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).