Luuk Spreeuwers

Papers

Total Citations

H-Index

About

Luuk Spreeuwers is a researcher whose work bridges computer vision, photogrammetry, and robotics, with a focus on solving real-world sensing and navigation challenges. His key research areas include camera network optimization, 3D modeling, and deep reinforcement learning for autonomous navigation. In his work on camera array design, Spreeuwers addresses the complex task of optimizing camera configurations for applications ranging from industrial metrology to biomedical engineering—a contribution that has earned early recognition with 3 citations. More recently, he has tackled the critical problem of shortcut learning in deep reinforcement learning for Object-Goal Navigation (ObjectNav), where robots must locate specific objects in unfamiliar environments. By proposing language-based augmentation strategies, Spreeuwers aims to make DRL agents more robust and generalizable, reducing their reliance on spurious correlations in simulation training. This work, with 2 citations, highlights his commitment to improving the reliability of AI-driven robotic systems. Spreeuwers’ research is particularly notable for its practical orientation, targeting deployment in homes and schools, and for addressing fundamental limitations in how machines perceive and interact with the physical world.