Max Robotics — Global Service Robot Directory + US Certification

About

Lingfei Mo is a researcher at the forefront of intelligent systems, whose work bridges the Internet of Things, robotics, and industrial automation. Mo’s key contributions span three critical areas: passive UHF-RFID localization, spiking neural networks for autonomous control, and deep learning for 3D point cloud and fault diagnosis. Their most impactful work, "Passive UHF-RFID Localization Based on the Similarity Measurement of Virtual Reference Tags" (2019, 31 citations), addresses a core challenge in IoT—achieving precise, low-cost indoor localization—by introducing a novel similarity-based method that eliminates the need for dense physical reference tags. Mo also pioneered unsupervised conditional reflex learning in "Convolutional Spiking Neural Network and Reward Modulation" (2020), offering a low-latency, computationally efficient solution for robot lane-keeping, a vital step toward practical autonomous navigation. Further advancing spatial AI, their work on "LPD-AE" (2020) provides a powerful latent space representation for large-scale 3D point clouds, enabling robust place recognition in dynamic environments. Most recently, Mo’s "MCAN-KAN" (2025) tackles the pressing industrial need for reliable fault diagnosis in complex manufacturing settings, using multi-scale attention to extract subtle defect features. With a growing citation record and a focus on deployable, real-world solutions, Mo’s research is shaping the future of smart, autonomous systems.