Erik Carlbaum

Papers

Total Citations

H-Index

About

Erik Carlbaum is a researcher focused on advancing autonomous robotic systems, with a particular emphasis on robust localization and perception in challenging environments. His work centers on enhancing vision-based odometry through deep learning, specifically by improving the extraction and tracking of distinctive image features—a critical capability for increasing robotic autonomy. Carlbaum’s notable contribution, "Towards Robust Localization Deep Feature Extraction by CNN" (2020), addresses the fragility of traditional feature extraction methods in difficult conditions such as low light, texture-poor scenes, or dynamic surroundings. By leveraging convolutional neural networks, he proposes a more resilient approach to feature detection, enabling robots to maintain accurate localization where conventional techniques fail. Although his cited work has garnered 2 citations to date, its conceptual foundation holds promise for real-world applications in autonomous navigation, from industrial inspection to search-and-rescue missions. Carlbaum’s research sits at the intersection of computer vision and robotics, offering practical solutions to one of the field’s persistent challenges: ensuring reliable spatial awareness in unpredictable settings. His contributions are particularly relevant for students and researchers exploring deep learning’s role in robust robotic perception.