# Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduit

arXiv: https://arxiv.org/abs/2512.10934 · HTML: https://mlsanity.com/paper/2512.10934/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [AlphaPilot: Autonomous Drone Racing](https://mlsanity.com/paper/2005.12813/) (2020)
- [Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigation](https://mlsanity.com/paper/2303.03207/) (2023)
- [LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments](https://mlsanity.com/paper/2102.03443/) (2021)
- [Colonoscopy Navigation using End-to-End Deep Visuomotor Control: A User Study](https://mlsanity.com/paper/2206.15086/) (2022)
- [BatMobility: Towards Flying Without Seeing for Autonomous Drones](https://mlsanity.com/paper/2307.11518/) (2023)
- [Autonomous Flights inside Narrow Tunnels](https://mlsanity.com/paper/2505.19657/) (2025)
- [Neither Fast Nor Slow: How to Fly Through Narrow Tunnels](https://mlsanity.com/paper/2201.03312/) (2022)
- [A Survey on LiDAR-based Autonomous Aerial Vehicles](https://mlsanity.com/paper/2509.10730/) (2025)
- [MAV Navigation in Unknown Dark Underground Mines Using Deep Learning](https://mlsanity.com/paper/2006.04223/) (2020)
- [3D Self-Localization of Drones using a Single Millimeter-Wave Anchor](https://mlsanity.com/paper/2310.08778/) (2023)
- [Neural-Geometric Tunnel Traversal: Localization-free UAV Flight with Tilted LiDARs](https://mlsanity.com/paper/2404.09688/) (2024)
- [Safe Navigation for Robotic Digestive Endoscopy via Human Intervention-based Reinforcement Learning](https://mlsanity.com/paper/2409.15688/) (2024)

## Abstract (arXiv)

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 approach enabling a drone to navigate unknown three-dimensional tubes without any prior knowledge of their geometry, relying solely on local observations from LiDAR 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 PPO policy acquires robust and generalizable behavior, consistently outperforming the deterministic controller despite its limited access to geometric information. Validation in a high-fidelity 3D environment further confirms the transferability of the learned behavior to a continuous physical dynamics. 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.