Zheyuan Wang
Papers
7
Total Citations
176
H-Index
5
About
Zheyuan Wang is a pioneering researcher at the intersection of multi-robot coordination, graph neural networks, and human-robot collaboration, with a particular focus on developing scalable, real-time scheduling solutions for complex multi-agent environments such as manufacturing facilities and warehouses. Wang's most influential contribution, "Learning Scheduling Policies for Multi-Robot Coordination With Graph Attention Networks" (2020, 89 citations), demonstrated how graph attention networks could be leveraged to solve combinatorially challenging scheduling problems that traditional exact methods struggle to handle efficiently. Building on this foundation, Wang extended the framework to heterogeneous settings, introducing temporospatial constraints and diverse communication strategies across a series of highly regarded works accumulating over 170 citations collectively. A recurring theme throughout Wang's research is bridging the gap between rigid classical optimization approaches and flexible, learning-based methods capable of handling stochastic, real-world conditions. More recently, Wang has explored recurrent neural scheduling and heterogeneous policy networks to enable intuitive human-robot teaming and adaptive agent communication. This body of work positions Wang as an emerging leader in intelligent multi-agent systems, offering meaningful advances for industries increasingly reliant on collaborative human-robot workforces.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7