Zhanhong Sun
Papers
2
Total Citations
17
H-Index
2
About
Dr. Zhanhong Sun is a leading researcher at the intersection of combinatorial optimization, multi-agent systems, and deep reinforcement learning. Their most impactful work introduces **DAN (Decentralized Attention-based Neural Network)**, a groundbreaking neural architecture designed to solve the notoriously difficult MinMax Multiple Traveling Salesman Problem (mTSP). This NP-hard challenge, critical for applications like warehouse robotics and drone fleet coordination, seeks to minimize the longest tour among all agents. Sun’s key contribution is a decentralized, attention-driven model that allows agents to dynamically compute near-optimal routes without a central controller, enabling scalable, real-time replanning in complex environments. With their seminal 2024 paper already garnering **12 citations** and a foundational 2021 version accumulating **5**, Sun’s work is rapidly shaping the future of autonomous coordination. By bridging the gap between theoretical optimization and practical robotic deployment, Dr. Sun is not just solving a classic problem—they are providing a blueprint for intelligent, scalable, and decentralized decision-making in multi-agent systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2