Max Robotics — Global Service Robot Directory + US Certification

About

Van Luan Tran is a leading researcher at the intersection of computer vision and robotics, specializing in 3D scene understanding, 6D pose estimation, and semantic segmentation. His work centers on developing advanced RGB-D camera systems and deep neural network architectures that enable robots to perceive and interact with their environments with high precision. Tran’s foundational contributions include the design of a structured light RGB-D camera for accurate depth measurement (25 citations), which directly addresses the critical need for reliable 3D data in industrial manipulation tasks. He further advanced the field by introducing BiLuNetICP, a deep neural network that simultaneously performs object semantic segmentation and 6D pose recognition (16 citations), demonstrating a powerful integration of detection and localization. His research consistently tackles the challenge of 6DoF pose estimation from RGB-D images, leveraging methods such as Mask R-CNN to improve object detection and pose recognition in cluttered scenes. With a total citation count exceeding 60 across his most-cited works, Tran’s contributions are pivotal for autonomous robotic manipulation, providing the perceptual foundations that allow robots to accurately grasp and handle objects in real-world settings.