Joshua Fabian

Papers

Total Citations

H-Index

About

Joshua Fabian is a robotics researcher whose work focuses on advancing visual odometry for mobile robots, particularly through the use of 3D sensors and RGB-D camera systems. His most influential paper, "Error Analysis for Visual Odometry on Indoor, Wheeled Mobile Robots With 3-D Sensors" (2014), has garnered 44 citations and stands as a foundational contribution to the field. In this work, Fabian systematically analyzes sensor noise and its propagation through the entire visual odometry pipeline, offering critical insights that improve the accuracy and reliability of robot localization in indoor environments. His earlier research, "One-Point Visual Odometry Using a RGB-Depth Camera Pair" (2012), introduces an innovative algorithm that leverages the Microsoft Kinect to perform visual odometry with minimal computational overhead. By detecting features using SURF and converting them into 3D locations, Fabian demonstrates how cost-effective sensors can achieve robust performance. Together, these contributions highlight Fabian’s expertise in sensor noise modeling, feature-based localization, and planar motion constraints—work that has practical implications for autonomous navigation in constrained indoor settings. His research remains a valuable resource for students and engineers developing wheeled mobile robots.