Max Robotics — Global Service Robot Directory + US Certification

About

Liguang Zhou is a robotics and computer vision researcher whose work spans scene understanding, quadruped robot locomotion, and lifelong learning systems. His research addresses fundamental challenges in robotic perception, with a particular focus on enabling robots to intelligently interpret and navigate complex real-world environments. Zhou's most impactful contributions lie in indoor scene recognition, where his papers "Object-to-Scene" (30 citations) and "BORM: Bayesian Object Relation Model" (17 citations) introduce innovative frameworks that transfer human-like object knowledge to enhance scene understanding — a critical capability for autonomous robots operating in unstructured spaces. His work on quadruped robotics, including posture correction for adaptive slope walking (15 citations) and turning strategy analysis (11 citations), demonstrates a strong foundation in physical robot control and gait engineering. Beyond perception and locomotion, Zhou has contributed meaningfully to human-robot interaction through long-range hand gesture recognition and has helped shape the broader research community by co-organizing the IROS 2019 Lifelong Robotic Vision Challenge (12 citations). His more recent work on lifelong monocular depth estimation and LiDAR depth completion reflects a growing commitment to continual learning and robust robot navigation, positioning him as a versatile contributor to next-generation intelligent robotic systems.