Van-Thanh Nguyen

Papers

Total Citations

H-Index

About

Van-Thanh Nguyen is a researcher advancing the intersection of computer vision and robotics, with a primary focus on visual-guided robotic manipulation. His work addresses a critical bottleneck in industrial automation: the need for high-precision, real-time object recognition and grasping. In his most cited paper (2019, 6 citations), Nguyen introduced a **Multi-Task Faster R-CNN** framework that simultaneously performs object detection and grasp planning, overcoming the limitations of conventional visual recognition methods for automated robot arms. This approach significantly enhances both speed and accuracy, making deep learning-based robotic systems more viable for real-world industrial deployment. In a related study (2019, 3 citations), he tackled the challenge of data scarcity by proposing a **self-supervised deep convolutional neural network** for robotic grasping, reducing the dependency on massive labeled datasets and mitigating overfitting. By pioneering these perception-driven learning strategies, Nguyen has contributed to making autonomous robotic systems more adaptable, efficient, and practical for manufacturing and logistics. His work continues to inspire further research into self-supervised and multi-task learning for intelligent robotics.