PhD Candidate in multi-sensor fusion and representation learning for underwater robotics
Core
Developing novel methods for multi-sensor fusion and representation learning using remote sensing priors to enhance underwater robot perception, localization, and adaptive survey planning.
Role type
PhD Candidate in multi-sensor fusion and representation learning for underwater robotics
Builds
Uncertainty-aware environmental models for benthic habitat mapping, infrastructure inspection, and persistent environmental monitoring
Domain
Underwater robotics, remote sensing, computer vision, machine learning
Deliverable
production ML models
Required skills
robotics, computer vision, state estimation, machine learning, statistical signal processing, Python, C++, mathematics
Preferred skills
sensor fusion, probabilistic state estimation, underwater perception, remote sensing image analysis, 3D reconstruction, foundation models, self-supervised representation learning, ROS2, robotics simulators, geospatial data tools
Technologies
Python, C++, ROS2, MBES, SAS, hyperspectral sensing
Responsibilities
Conduct and publish high-quality research; develop implementable methods for onboard robot perception and survey planning; conduct experimental deployments and field evaluations using AUVs; supervise master's thesis students; participate in international conferences and research stays
Seniority
PhD Candidate, research-focused