Zhexin Shen
Papers
1
Total Citations
8
H-Index
1
About
Zhexin Shen is a researcher at the forefront of multi-agent robotics, specializing in the coordination of heterogeneous teams that combine unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). His work addresses critical challenges in deploying these mixed teams for high-stakes applications such as disaster rescue, precision agriculture, and military missions. Shen’s most-cited paper, "Proficiency Constrained Multi-Agent Reinforcement Learning for Environment-Adaptive Multi UAV-UGV Teaming" (2021, 8 citations), introduces a novel reinforcement learning framework that enables robot teams to dynamically adapt their configurations based on environmental conditions and individual robot proficiencies. This contribution is significant because it tackles the fundamental problem of varying team capabilities—where robots differ in sensing, mobility, and task execution—by learning optimal task allocation and coordination policies. By integrating proficiency constraints into multi-agent learning, Shen’s work advances the practical deployment of autonomous systems in unpredictable real-world settings. His research bridges the gap between theoretical multi-agent systems and operational robotics, offering scalable solutions for complex, environment-adaptive teaming.
Research Focus
Key Achievements
Top Papers
- 1