Junnan Zhang
Papers
1
Total Citations
10
H-Index
1
About
Junnan Zhang is a leading researcher in intelligent robotics and automation, with a core focus on multi-robot coordination, task assignment, and deep reinforcement learning (DRL). His most cited work, “Multi‐station multi‐robot task assignment method based on deep reinforcement learning” (2024, 10 citations), introduces a novel DRL framework that integrates a public graph attention network with independent policy networks to solve complex multi-station spot welding assignments. This contribution addresses a critical bottleneck in manufacturing: efficiently allocating tasks across multiple robots in dynamic environments. Zhang’s approach encodes the spatial distribution of welding spots, enabling scalable, real-time decision-making that outperforms traditional heuristic methods. His research bridges the gap between theoretical reinforcement learning and practical industrial applications, demonstrating how graph neural networks can enhance robotic collaboration. By tackling real-world constraints like station layouts and robot capabilities, Zhang’s work has immediate implications for smart factories and automated production lines. His achievements highlight a deep commitment to advancing autonomous systems, making him a key figure in the evolution of intelligent manufacturing and multi-agent robotics.
Research Focus
Key Achievements
Top Papers
- 1