Max Robotics — Global Service Robot Directory + US Certification

About

Quang-Tri Duong is a rising star in computer vision and robotics, whose research focuses on bridging the gap between perception and manipulation. His work centers on three interconnected challenges: object pose estimation, hand-object interaction modeling, and robotic grasp detection. Duong’s major contributions include developing graspability-aware pose estimation methods that enable robots to recognize not just an object’s location, but whether it can be successfully grasped in cluttered scenes. He has pioneered multi-modal fusion techniques that combine color and depth data with attention mechanisms, achieving robust performance even when traditional depth sensors fail. His most cited paper (18 citations) addresses object pose estimation in cluttered environments, while his work on hand-object pose estimation (11 citations) advances augmented reality and imitation learning applications. Duong’s attention-based grasp detection framework, which works with monocular depth estimation, reduces reliance on expensive 3D sensors. With all five of his most cited papers published in 2024, Duong represents a new generation of researchers rapidly advancing the state of the art in robotic manipulation—making robots that can see, understand, and grasp objects more reliably than ever before.