Hai-Dang Kieu
Papers
1
Total Citations
2
H-Index
1
About
Hai-Dang Kieu is a researcher at the forefront of integrating deep reinforcement learning with robotic navigation, with a particular focus on how artificial agents can leverage visual memory to locate and approach target objects. His most-cited work, "Vision Memory for Target Object Navigation Using Deep Reinforcement Learning: An Empirical Study" (2018), provides a foundational empirical investigation into how neural networks can learn spatial and semantic features from high-dimensional visual data, while reinforcement learning enables systems to improve through trial-and-error experience. This study has garnered 2 citations and serves as a practical guide for designing memory-augmented navigation policies. Kieu’s research addresses a critical challenge in embodied AI: enabling robots to not only see but remember where objects are located in complex, dynamic environments. By bridging computer vision and decision-making, his contributions help pave the way for more autonomous and adaptable robotic systems. His work is particularly valuable for students and researchers exploring the intersection of deep learning, memory architectures, and goal-driven navigation—a rapidly growing area with applications in service robotics, autonomous vehicles, and intelligent surveillance.
Research Focus
Key Achievements
Top Papers
- 1