Max Robotics — Global Service Robot Directory + US Certification

About

Mohammad Bozorg is a researcher whose work sits at the intersection of autonomous robotics, navigation, and state estimation — fields that are increasingly central to modern intelligent systems. He is perhaps best known for his contributions to Simultaneous Localization and Mapping (SLAM), with his 2017 paper "SLAM in Dynamic Environments via ML-RANSAC" becoming his most influential work, accumulating 67 citations and offering a robust solution for robots operating in unpredictable, real-world settings. Building on this foundation, his 2019 adaptive Unscented Kalman Filter (UKF) approach further refined SLAM accuracy, earning 21 citations and demonstrating his commitment to iterative algorithmic improvement. Bozorg has also made notable contributions to underwater vehicle dynamics, applying Extended Kalman Filtering with ARMA noise modeling to improve the identification and simulation of autonomous underwater vehicles — work that has garnered 25 citations and holds clear practical value for marine robotics engineers. His research additionally spans decentralized sensor fusion for indoor localization and fault detection in navigation architectures, reflecting a broad and systems-level perspective on autonomous vehicle reliability. Taken together, his body of work offers meaningful advances in making autonomous systems smarter, more accurate, and more resilient.