Hong-Qi Chu

National Taipei University of Technology

Papers

Total Citations

H-Index

About

Hong-Qi Chu is a robotics researcher whose work focuses on advancing robotic grasping through deep learning and computer vision. His primary research areas include robotic manipulation, grasp detection algorithms, and the application of convolutional neural networks to real-world automation challenges. Chu’s major contribution lies in pioneering the use of Rotation Region CNNs (R2CNN) for robotic grasp detection—a method that overcomes the limitations of traditional vertical bounding box approaches by directly predicting oriented grasping rectangles. His 2021 paper, “Robotic Grasp Detection by Rotation Region CNN,” has garnered 5 citations and introduced a more efficient pipeline that eliminates the need for post-processing steps common in earlier one- or two-stage detectors. Building on this, his 2024 work, “Enhancing Robotic Grasping Detection Accuracy With the R2CNN Algorithm and Force-Closure,” extends the framework to practical applications like supermarket item retrieval, achieving higher accuracy through force-closure analysis without architectural modifications. Though early in his career, Chu’s innovative approach to grasp detection—combining rotational region proposals with stability constraints—positions him as a promising contributor to the field of intelligent robotics, with potential impact on warehouse automation and service robots.