Metraipolis › archive › dc_fa31e979a2bb
Unified Planning-Learning Framework for Robust UUV Navigation Under Partial Observability — arXiv:2608.05365
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05365
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:38:11.487Z
- SHA-256 of the archived text
880d838730383445eaaaaa3b0f3c10b54da9e12be4015f9937096e3c8d8d1c09- Stable URL of this page
https://metraipolis.com/documento/dc_fa31e979a2bb
How to cite
Unified Planning-Learning Framework for Robust UUV Navigation Under Partial Observability — arXiv:2608.05365 — arXiv (en), https://arxiv.org/abs/2608.05365 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa31e979a2bb (Metraipolis archive dc_fa31e979a2bb, sha256 880d838730383445eaaaaa3b0f3c10b54da9e12be4015f9937096e3c8d8d1c09)
BibTeX
@misc{dcfa31e979a2bb,
title = {Unified Planning-Learning Framework for Robust UUV Navigation Under Partial Observability — arXiv:2608.05365},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05365},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa31e979a2bb; sha256 880d838730383445eaaaaa3b0f3c10b54da9e12be4015f9937096e3c8d8d1c09},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05365. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents an observation-only autonomy framework for Unmanned Underwater Vehicles (UUVs) navigation in dynamic underwater environments that integrates persistent occupancy mapping, global clearance-aware planning, and risk-aware local control. The proposed pipeline constructs occupancy maps solely from onboard sonar and depth image observations, adapts a clearance-constrained global planner (GP) to provide long-horizon structure, and integrates a reinforcement learning (RL) policy to handle short-range tracking and reactive avoidance. To further support decision-making under partial observability, the system learns a compact latent state representation from onboard sensor data, encoding environmental structure, obstacle dynamics, and uncertainty. Behavior tree (BT) distillation with staged supervision is introduced to improve safety and training stability, while an uncertainty-calibrated distillation mechanism reweights teacher guidance using online latent-model uncertainty, emphasizing uncertain regimes during learning, with time-to-collision (TTC) and clearance cues remaining explicit in planning and local policy features. To demonstrate the efficacy of the framework, a reproducible multi-seed evaluation protocol is established in high-fidelity GPU-accelerated simulation using NVIDIA Isaac Sim, and performance is benchmarked against BT-only and standard RL baselines. The results obtained demonstrate improved robustness and safety under dynamic conditions, thus providing a general pipeline with a unified hybrid planning learning architecture and a reproducible methodology for robust UUV autonomy under partial observability. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.05365 — 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 2026-10-31T10:24:02.084Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).