This special session focuses on recent advances in learning-based state estimation and navigation, leveraging data-driven techniques such as deep learning and reinforcement learning, with applications spanning platforms such as unmanned aerial vehicles (UAVs), ground robots, smartphones, and wearable devices. Topics include learning-enhanced inertial navigation, visual navigation, multi-sensor fusion, wireless and GNSS-based localization, robust and safety-aware localization, and adaptive estimation frameworks. The session aims to highlight how learning techniques enable reliable and accurate navigation in complex environments, where conventional sensing modalities are often degraded or unavailable.
