Max Robotics — Global Service Robot Directory + US Certification

About

Menglong Zhu is a leading researcher in computer vision and robotics, specializing in 3D object perception, semantic localization, and human-robot teaming. His most influential work, "Single image 3D object detection and pose estimation for grasping" (227 citations), introduced a novel deformable parts-based model that enables robots to detect objects and estimate their 3D pose from single images of cluttered scenes—even without texture cues—significantly advancing robotic grasping capabilities. Zhu has also made foundational contributions to semantic localization, developing approaches that leverage object recognition to localize robots within prior maps of landmarks, moving beyond traditional geometric features. His papers on this topic, including "Localization from semantic observations via the matrix permanent" (67 citations) and "Semantic Localization Via the Matrix Permanent" (62 citations), have been widely cited for their innovative use of the matrix permanent to handle ambiguous semantic observations. As part of the US Army Research Laboratory's Robotics Collaborative Technology Alliance, Zhu contributed to integrated intelligence for human-robot teams and demonstrated progress in robotic perception and semantic navigation, helping to transform robots from tools into collaborative teammates.