High accuracy underwater inspections are getting more and more important in the underwater industry where time and cost optimization represent nowadays the main innovation drivers. The subsea industry is undergoing a digital transformation process and for this reason, methods that can provide real-time accurate 3D digital measurements are increasingly demanded. This paper provides a short review of the main techniques currently used in subsea metrology to then present an experimental study carried out to evaluate the accuracy potential of three vision-based techniques well-known in photogrammetry, namely visual odometry with and without windowed bundle adjustment, and keyframe based simultaneous localization and mapping (SLAM). The accuracy evaluation is done using an ORUS 3D ® subsea photogrammetry system using a certified 3D underwater reference test-field available at COMEX facilities, whose spatial coordinates are known with sub-millimetre accuracy. A critical assessment of results is presented against currently set tolerances for the subsea metrology industry.
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.