Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduits
Sensors · 13.02.2026 · 26 (4) · 1236
DOI: 10.3390/s26041236 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.02.2026. Verfasst von Zamirddine Mari und 2 weiteren Autor:innen. Beteiligte Einrichtung: DGA Techniques Navales-Direction Générale de l'Armement, Toulon, France. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Interreg Italy-France Maritime Program 2021-2027.
Abstract (Originalsprache)
Autonomous drone navigation in confined tubular environments remains a major challenge due to the constraining geometry of the conduits, the proximity of the walls, and the perceptual limitations inherent to such scenarios. We propose a reinforcement learning (RL) approach enabling a drone to navigate unknown three-dimensional tubes without any prior knowledge of their geometry, relying solely on local observations from a Light Detection and Ranging (LiDAR) sensor and a conditional visual detection of the tube center. In contrast, the Pure Pursuit algorithm, used as a deterministic baseline, benefits from explicit access to the centerline, creating an information asymmetry designed to assess the ability of RL to compensate for the absence of a geometric model. The agent is trained through a progressive curriculum learning strategy that gradually exposes it to increasingly curved geometries, where the tube center frequently disappears from the visual field. A turning-negotiation mechanism, based on the combination of direct visibility, directional memory, and LiDAR symmetry cues, proves essential for ensuring stable navigation under such partial observability conditions. Experiments show that the Proximal Policy Optimization (PPO) policy acquires robust and generalizable behavior, consistently outperforming the deterministic controller despite its limited access to geometric information. Validation in a high-fidelity three-dimensional environment further confirms the transferability of the learned behavior to continuous physical dynamics. In particular, this work introduces an explicit formulation of the turn negotiation problem in tubular navigation, coupled with a reward design and evaluation metrics that make turn-handling behavior measurable and analyzable. This explicit focus on turn negotiation distinguishes our approach from prior learning-based and heuristic methods. The proposed approach thus provides a complete framework for autonomous navigation in unknown tubular environments and opens perspectives for industrial, underground, or medical applications where progressing through narrow and weakly perceptive conduits represents a central challenge.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- DGA Techniques Navales-Direction Générale de l'Armement, Toulon, France.
- LIRMM, TETIS, CNRS, Université de Montpellier Paul-Valéry, Montpellier, France.
- Université de Toulon, Aix Marseille Univ, CNRS, LIS, Marseille, France.
ORCID-Profile: Zamirddine Mari, Jérôme Pasquet, Julien Seinturier
Förderung
- Interreg Italy-France Maritime Program 2021-2027
Zitieren
APA
Mari, Z., Pasquet, J., & Seinturier, J. (2026). Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduits. Sensors, 26(4), 1236. https://doi.org/10.3390/s26041236
Vancouver
Mari Z, Pasquet J, Seinturier J. Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduits. Sensors. 2026;26(4):1236. doi:10.3390/s26041236
BibTeX
@article{Mari2026,
author = {Mari, Zamirddine and Pasquet, Jérôme and Seinturier, Julien},
title = {Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduits},
journal = {Sensors},
year = {2026},
volume = {26},
number = {4},
pages = {1236},
doi = {10.3390/s26041236}
}
EUVIMED