Roberto Pellerito

Papers

Total Citations

H-Index

About

Roberto Pellerito is a robotics researcher specializing in visual odometry and sensor fusion for autonomous navigation in challenging environments. His work focuses on integrating event-based cameras with traditional frame-based sensors to enhance robotic perception in GPS-denied settings, such as planetary terrains and low-light conditions. His most-cited paper, "Deep Visual Odometry with Events and Frames" (2024, 12 citations), introduces a novel deep learning approach that combines the complementary strengths of event cameras—which excel in high-speed motion and poor lighting—with conventional cameras to achieve robust, real-time pose estimation. This contribution addresses a critical gap in autonomous navigation, where standard visual odometry often fails under rapid motion or extreme illumination. Pellerito’s research has been recognized for its potential impact on space exploration and field robotics, with his work cited by peers advancing sensor fusion and deep learning for mobile robots. His achievements include developing algorithms that push the boundaries of visual odometry reliability, making him a notable emerging voice in the intersection of computer vision and robotics.