What to expect:

In search and rescue operations, occlusions caused by forests and complex environments can reduce the ability of UAVs to efficiently detect and map areas of interest. Visibility-aware navigation offers the possibility of improving search efficiency by directing drones toward viewpoints that maximize information gain. By combining computer vision methods with LiDAR sensing and multi-UAV coordination, visibility maps can be generated and used to guide collaborative drone systems. The aim of this thesis is to investigate and develop methods that enable intelligent visibility-based guidance strategies for UAV swarms.

Your tasks:

• Investigate state-of-the-art methods for visibility estimation and visibility-aware guidance in multi-UAV systems
• Develop computer vision approaches for generating visibility maps from sensor data
• Implement and evaluate algorithms in simulation and on real UAV platforms
• Conduct field experiments using UAVs equipped with LiDAR sensors
• Analyze, validate, and document experimental results

Your profile: 

• Master's student in Robotics, Computer Science, Electrical Engineering, Geomatics, or a related field
• Strong programming skills in Python and/or C++
• Background in computer vision, robotics, or perception methods
• Interest in research and experimental work involving UAV systems
• Experience with ROS, LiDAR processing, or simulation environments is an advantage
• Ability to work independently with a self-motivated approach