Metraipolis › archive › dc_ed2932258ef6

Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles — arXiv:2608.08598

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08598
License (as archived)
CC0-1.0
Archived
2026-10-19T09:12:36.066Z
SHA-256 of the archived text
f4c558faa0d6b7b966c2a39aede591fa9f251b60f84fa448dce1e269610bb779
Stable URL of this page
https://metraipolis.com/documento/dc_ed2932258ef6

How to cite

Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles — arXiv:2608.08598 — arXiv (en), https://arxiv.org/abs/2608.08598 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed2932258ef6 (Metraipolis archive dc_ed2932258ef6, sha256 f4c558faa0d6b7b966c2a39aede591fa9f251b60f84fa448dce1e269610bb779)
BibTeX
@misc{dced2932258ef6,
  title = {Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles — arXiv:2608.08598},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08598},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed2932258ef6; sha256 f4c558faa0d6b7b966c2a39aede591fa9f251b60f84fa448dce1e269610bb779},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08598. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the continuous improvement of computational capabilities, end-to-end reinforcement learning has been rapidly developed for remotely operated vehicles control. Nevertheless, existing end-to-end reinforcement-learningbased methods still face challenges in achieving optimal control under oceancurrent disturbances. In particular, there remains a lack of a unified control framework that can simultaneously achieve low steady-state tracking error, rapid transient response, energy-efficient operation, and smooth controlforce outputs under disturbances. To address the issue, this paper proposes the thrust smoothness rapid current adaptation proximal policy optimization (TSRCA-PPO) method which learns a near-optimal strategy by a twostage distillation learning framework. The core innovations of this work lie in the reward-function design and the privileged multi-encoder architecture. Ablation studies validate the effectiveness of each module. Simulation results demonstrate that the proposed TSRCA-PPO method consistently outperforms the conventional cascaded P-PID controller across all evaluation metrics. Specifically, TSRCA-PPO reduces the steady-state position error, steady-state attitude error, settling time, energy index, and thrustsmoothness index to 42.7%, 76.5%, 10.6%, 93.5%, and 15.9% of the corresponding P-PID values, respectively.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.08598 — 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 2026-10-19T09:11:58.749Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).