PhD in Robotics

Unmanned aerial and surface platforms are increasingly deployed for maritime monitoring, environmental assessment, search-and-rescue, and pollution detection./nThe central challenge lies in recovering reliable environmental parameters from water-surface imagery in which multiple physical factors are tightly coupled. Illumination angle, spectral composition, wave geometry, surface reflection and cloud attenuation jointly shape the visual signal, making it difficult to attribute observed features to any single cause./nThis project introduces a physics-informed inverse modelling framework that decouples multi-factor water-surface imaging through deep neural inference and optical priors. A controlled experimental platform will replicate ocean surface optics in a large water-tank facility, generating paired datasets across variable illumination, wave states and turbidity, enabling hybrid deep-learning and iterative optimisation solutions with clear lab-to-field transferability.