Master Thesis - Vision Foundation Models for automated point cloud map cleanup

Was Sie bei uns tun

In this thesis you will explore the use of vision foundation models within robot localization. Specifically, you will utilize DINOv2 (or similar) features to enable efficient map cleanup, which might be self-learning by utilizing an online dynamic object removal/detection technique. The usability of such a map as reference for real-time robot localization will then be evaluated.

Was Sie mitbringen

• Enrolled student


• Background in Computer Science, Software Engineering, Electrical Engineering, Autonomous Systems or similar


• Knowledge of C++/Python


• Experience with ROS, computer vision, pointcloud-processing or machine learning is a plus


• Analytical mindset and experience...