Kuan-kian Heng
Papers
1
Total Citations
25
H-Index
1
About
Kuan-kian Heng is a researcher advancing the field of autonomous navigation through deep reinforcement learning. His primary focus lies in developing intelligent agents capable of navigating complex, dynamic environments. His most notable contribution is the "iTD3-CLN" framework, introduced in his 2022 paper, which has garnered 25 citations. This work addresses a critical challenge in robotics and AI: enabling agents to learn robust navigation policies that adapt to moving obstacles and changing surroundings. By integrating a twin-delayed deep deterministic policy gradient (TD3) algorithm with a curriculum learning strategy, Heng's approach significantly improves sample efficiency and safety in training. His research bridges the gap between theoretical reinforcement learning and practical deployment in real-world scenarios, such as autonomous vehicles and service robots. While still early in his career, Heng's work has already influenced subsequent studies in dynamic navigation, demonstrating the potential of his methods. His contributions are particularly valuable for students and researchers seeking to understand how deep RL can be applied to real-time decision-making under uncertainty, making him a promising voice in the intersection of machine learning and robotics.
Research Focus
Key Achievements
Top Papers
- 1