Max Robotics — Global Service Robot Directory + US Certification

About

Jingbin Liu is a leading researcher in autonomous navigation and spatial intelligence, whose work bridges the critical gap between precise positioning and robust perception in dynamic environments. His core research spans LiDAR odometry, semantic SLAM, and multi-sensor fusion for indoor and outdoor localization. Liu’s major contributions include developing a LiDAR-based single-shot global localization solution using a cross-section shape context descriptor (52 citations), which enables rapid, accurate place recognition without prior maps. He also pioneered a computationally efficient semantic SLAM system (51 citations) that filters dynamic objects like pedestrians, significantly improving mapping accuracy in cluttered scenes. His innovative CAE-LO framework (21 citations) leverages unsupervised convolutional auto-encoders for interest point detection, advancing deep learning in LiDAR odometry. Liu’s comprehensive survey on UWB and Wi-Fi RTT positioning technologies (15 citations) provides a roadmap for sub-meter indoor accuracy, essential for IoT and robotics. His early work on knowledge-based indoor positioning using LiDAR-aided multi-sensor systems (12 citations) laid the foundation for low-cost, robust UGV navigation. With a 2025 publication on real-time motion state estimation for visual-inertial odometry in dynamic scenes, Liu continues to push the boundaries of reliable autonomous navigation. His work has been widely cited across robotics, autonomous driving, and smart manufacturing communities.