Do-Van Nguyen

Papers

Total Citations

H-Index

About

Do-Van Nguyen is a researcher advancing autonomous navigation and computer vision through deep learning. His primary research areas include reinforcement learning for robotic navigation, semantic image segmentation, and vision-based memory systems for intelligent agents. Nguyen’s most impactful work, “Reinforcement Learning Based Navigation with Semantic Knowledge of Indoor Environments” (2019, 21 citations), introduces a novel framework that integrates semantic understanding of indoor spaces into deep reinforcement learning, enabling robots to learn and plan more effectively in complex environments. This contribution addresses a critical challenge in autonomous robotics—bridging high-level scene comprehension with low-level action policies. In “Real-Time Image Semantic Segmentation Networks with Residual Depth-Wise Separable Blocks” (2018, 5 citations), Nguyen develops efficient architectures for pixel-level scene understanding, a key enabler for applications like autonomous vehicles. His empirical study on vision memory for target object navigation (2018, 2 citations) further explores how neural networks can retain and utilize spatial information to improve goal-directed behavior. Nguyen’s work demonstrates a focused effort to make autonomous systems more intelligent and context-aware, with potential impacts on service robotics, smart environments, and self-driving technology.