Xiaoqiang Zhang

Southwest University of Science and Technology

Papers

Total Citations

H-Index

About

Xiaoqiang Zhang is a researcher specializing in robotic perception and intelligent automation, with a particular focus on deep learning-based grasp detection systems for autonomous robotics. His work sits at the intersection of computer vision, neural network design, and human-robot interaction, addressing critical challenges in enabling robots to operate independently and intelligently in real-world environments. Zhang's most notable contribution, *DSC-GraspNet* (2023), demonstrates his commitment to solving a fundamental tension in the field: balancing detection accuracy with computational efficiency. By developing a lightweight convolutional neural network architecture, he tackled the persistent shortcoming of existing learning-based methods that struggled to achieve both high precision and low processing time simultaneously. This work also extends its relevance to virtual reality-based teleoperation, broadening its applicability beyond traditional robotics into emerging human-machine interface technologies. The paper has garnered 17 citations since its publication, reflecting growing interest from the robotics and computer vision communities. Zhang's research represents a meaningful step toward more practical and deployable robotic systems, making his work particularly valuable for researchers and engineers working on autonomous manipulation, smart manufacturing, and next-generation teleoperation platforms.