Papers
8
Total Citations
114
H-Index
7
About
Zhiqiang Pu is a leading researcher in multi-robot systems and deep reinforcement learning (DRL), whose work addresses fundamental challenges in cooperative autonomy. His research focuses on developing intelligent, distributed control policies for multi-agent teams operating in dynamic and uncertain environments. Pu’s major contributions center on solving complex coordination problems—formation control, multi-target coverage with connectivity guarantees, and target encirclement—while ensuring collision avoidance. He pioneered the integration of model-based paradigms with DRL for formation control (29 citations) and introduced relational graph-based architectures that allow robots to learn transferable, decentralized policies for encirclement tasks (16 citations). His work on connectivity-guaranteed coverage (20 citations) and navigation among autonomous agents using graph attention networks (12 citations) has been highly influential. Pu’s innovative use of knowledge-incorporated policy frameworks and hierarchical DRL for subgoal-guided navigation demonstrates his ability to bridge theoretical advances with practical deployment. With a growing citation record and a portfolio of high-impact papers, Pu is shaping the future of safe, scalable multi-robot coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8