Max Robotics — Global Service Robot Directory + US Certification

About

Zhaoxiang Liu is a researcher whose work sits at the intersection of deep learning, computer vision, and robotics, with a particular focus on intelligent autonomous systems and human-robot interaction. His most celebrated contribution, "Deep Learning Based Robot for Automatically Picking Up Garbage on the Grass" (2018), has accumulated over 160 citations and demonstrates his ability to translate cutting-edge neural network techniques into practical robotic applications — combining deep learning-based garbage detection with sophisticated ground segmentation for autonomous navigation. Liu has also made meaningful strides in visual localization and odometry, proposing end-to-end deep networks that address the persistent drift problem in long-term robot navigation, as well as a feedback mechanism-based stereo visual-inertial SLAM system balancing accuracy with real-time performance. His work on facial pose estimation using label distributions reflects a broader interest in perceptual intelligence for human-robot interaction, gaze estimation, and driver monitoring. Earlier contributions to agricultural robotics — including multi-spectral vision systems for apple maturity detection and 3D sensing — reveal a career-long commitment to deploying intelligent vision in real-world environments. More recently, Liu has explored multimodal activity detection for virtual human interaction, extending his research into emerging metaverse applications.