Metraipolis › archive › dc_4e45d17974db

Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation — arXiv:2610.41892

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41892
License (as archived): CC0-1.0
Archived: 2026-11-03T08:22:26.734Z
SHA-256 of the archived text: fd22ee1d19bae2357e39649e875ee786ab5ba53538c60fdcddc848314dd5cb26
Stable URL of this page: https://metraipolis.com/documento/dc_4e45d17974db

How to cite

Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation — arXiv:2610.41892 — arXiv (en), https://arxiv.org/abs/2610.41892 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e45d17974db (Metraipolis archive dc_4e45d17974db, sha256 fd22ee1d19bae2357e39649e875ee786ab5ba53538c60fdcddc848314dd5cb26)

BibTeX

@misc{dc4e45d17974db,
  title = {Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation — arXiv:2610.41892},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41892},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e45d17974db; sha256 fd22ee1d19bae2357e39649e875ee786ab5ba53538c60fdcddc848314dd5cb26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41892. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How to reuse a pretrained locomotion policy for precise loco-manipulation is still an open problem. We propose an online method to learn the closed-loop dynamics under a frozen locomotion policy. The learned model predicts floating-base motion and improves loco-manipulation accuracy. However, unobserved latent conditions of the policy introduce heterogeneous responses, meaning that the same observed state will lead to different motions. Direct learning without accounting for this heterogeneity introduces bias and fluctuations into dynamics estimates, degrading floating-base prediction and end-effector tracking. To address this problem, a contaminated Gaussian model is proposed to approximate the effects of latent conditions. The model uses two Gaussian components to approximate predictable and unpredictable responses under the same observed state. Then, the contaminated Gaussian model is combined with a Gaussian process to construct an online learner using random Fourier features (RFFs). The learner estimates each response's probability of belonging to the predictable component and uses it to weight online updates, capturing predictable responses while reducing bias and fluctuations caused by heterogeneous observations. With consistent and unbiased dynamics estimates, model predictive control (MPC) predicts floating-base motion accurately and enables precise loco-manipulation. A finite-sample error bound is established to ensure uniform convergence in online learning. Simulation and hardware experiments demonstrate consistent end-effector tracking across different manipulator configurations and tasks, with errors of 0.01 m.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41892 — 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 2026-11-03T08:06:53.844Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).