Max Robotics — Global Service Robot Directory + US Certification

About

Bojian Liang is a computer vision researcher whose work has made significant contributions to the field of mobile robot visual navigation, with a particular focus on ground plane segmentation and homography-based navigation techniques. Working primarily in the early-to-mid 2000s, Liang developed innovative methods enabling mobile robots to navigate autonomously using monocular, uncalibrated cameras — a notably challenging constraint that broadened the practical applicability of robot vision systems. His most impactful contributions include the development of H-based tracking, a technique that groups corner points into coplanar regions to detect and segment ground planes from image sequences, and the introduction of novel homography-based results enabling mobile robots to perform visual navigation using as few as two pairs of corresponding features. These two works have garnered 61 and 60 citations respectively, establishing them as foundational references in the field. Liang further extended this research by integrating multiple visual cues — color, contours, and corner motion — to improve segmentation robustness, and by developing methods allowing robots to determine whether obstacles can be driven over, driven under, or avoided entirely. His body of work represents a cohesive and practically oriented research program that meaningfully advanced autonomous robot perception.