Max Robotics — Global Service Robot Directory + US Certification

About

Ming Tang is a robotics researcher whose work centers on advancing Simultaneous Localization and Mapping (SLAM) algorithms for autonomous navigation. Tang’s primary contributions lie in improving the accuracy and robustness of SLAM systems through novel filtering techniques. Their most-cited paper, "Robot Tracking in SLAM with Masreliez-Martin Unscented Kalman Filter" (2020, 26 citations), introduces a method that enhances state estimation under non-Gaussian noise conditions. Tang has also developed "SLAM with Improved Schmidt Orthogonal Unscented Kalman Filter" (2022, 11 citations), which reduces computational complexity while maintaining precision. Further innovations include "An Improved Adaptive Unscented FastSLAM with Genetic Resampling" (2021, 10 citations) and "An improved H-infinity unscented FastSLAM with adaptive genetic resampling" (2020, 9 citations), both of which integrate genetic algorithms to optimize resampling steps, mitigating particle depletion in FastSLAM. With a cumulative citation count exceeding 56, Tang’s work is recognized for bridging theoretical filtering advances with practical SLAM implementation, offering solutions that balance efficiency and reliability—critical for real-time robotics applications. Their research continues to influence the development of more resilient autonomous systems.