Luca Caltagirone

Papers

Total Citations

H-Index

About

Luca Caltagirone is a researcher whose work sits at the intersection of robotics, autonomous navigation, and 3D perception. His primary contributions focus on enabling mobile robots and autonomous vehicles to understand and traverse complex, unstructured environments. His most-cited work, "Learning Traversability From Point Clouds in Challenging Scenarios" (2017, 39 citations), is a foundational study that evaluates the use of support vector machine (SVM) classifiers for detecting road traversability from LiDAR point cloud data. By systematically testing four different kernel functions on both urban and extra-urban datasets, Caltagirone demonstrated how machine learning can effectively interpret sparse 3D data to identify safe, drivable paths. This work directly addresses a critical challenge in field robotics: navigating off-road or cluttered terrains where traditional mapping fails. His research has helped bridge the gap between raw sensor data and high-level navigation decisions, providing practical, data-driven solutions for autonomous systems operating in the real world. Through his focus on robust feature extraction and classification from point clouds, Caltagirone has made a tangible impact on the development of safer and more capable autonomous vehicles.