This session will highlight recent research results on AI-driven methods for visual simultaneous localization and mapping (VSLAM) in underwater environments.
Deep learning algorithms that combine geometric constraints have been developed to enhance robustness and efficiency, particularly in low-visibility and dynamic environments. Building on these foundations, the approach has been extended toward real-time, camera-based navigation for autonomous underwater vehicles. Results from experimental evaluations on field datasets demonstrate how the integration of deep learning and geometric reasoning can advance the resilience, precision, and reliability of underwater robotic localization beyond traditional methods. The work was performed within a Marie-Curie Action REMARO (Horizon2020) and DeepODO project (Innovation Fund Denmark).
Speakers: