Papers
3
Total Citations
12
H-Index
2
About
Hui Zeng is a researcher advancing the frontiers of autonomous robotics through deep reinforcement learning, with a focus on safe and socially-aware navigation in dense human crowds. Their most cited work, "Robot Navigation in Crowd Based on Dual Social Attention Deep Reinforcement Learning" (2021, 7 citations), introduces a novel dual-attention mechanism that enables robots to find collision-free, socially compliant paths in complex, dynamic environments—a critical challenge for service robots operating in public spaces. Zeng also addresses practical industrial applications, developing a deep reinforcement learning-based sorting method for manipulators handling radioactive waste (2022, 3 citations), improving efficiency and autonomy in hazardous settings. Additionally, their research on intelligent voice interaction systems using the NAO robot (2020, 2 citations) explores human-robot communication. While still early in their career, Zeng’s work bridges theoretical advances in reinforcement learning with real-world robotic deployment, particularly in crowded and unstructured environments. Their contributions are paving the way for more capable, autonomous robots that can operate safely alongside humans.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3