Metraipolis › archive › dc_afa6e997dc64
Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning — arXiv:2610.20925
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20925
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:25:04.629Z
- SHA-256 of the archived text
08918daa1796d9220ec812f95514c0a4cc6a41ac23e7dcdd2dd04834c7217b0a- Stable URL of this page
https://metraipolis.com/documento/dc_afa6e997dc64
How to cite
Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning — arXiv:2610.20925 — arXiv (en), https://arxiv.org/abs/2610.20925 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afa6e997dc64 (Metraipolis archive dc_afa6e997dc64, sha256 08918daa1796d9220ec812f95514c0a4cc6a41ac23e7dcdd2dd04834c7217b0a)
BibTeX
@misc{dcafa6e997dc64,
title = {Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning — arXiv:2610.20925},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20925},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afa6e997dc64; sha256 08918daa1796d9220ec812f95514c0a4cc6a41ac23e7dcdd2dd04834c7217b0a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20925. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robust adaptive control is vital for keeping robots safe while actively reducing uncertainty in unfamiliar settings. However, traditional methods are often conservative since they fail to account for guaranteed future parameter learning during planning and struggle to scale to high-dimensional systems. In this work, we present A-SLS, a learning-aware robust adaptive model predictive control (RAMPC) framework based on system-level synthesis. A-SLS forecasts future parameter uncertainty and preserves correlations between process disturbances, parameter error, and estimate updates to construct tight, guaranteed reachable sets that account for future information gain. We also develop a GPU-accelerated A-SLS solver to enable real-time performance. Across nonlinear robotic systems, A-SLS reduces reachable-tube conservativeness, maintains real-time performance, and scales to whole-body control for a quadruped with 61 states, 8 uncertain parameters, and 12 control inputs. We further demonstrate the approach on hardware, where a physical Crazyflie drone learns an uncertain dynamics parameter online to stabilize on the fly. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG); Systems and Control (eess.SY); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2610.20925 — 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 2026-10-16T08:48:02.864Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).