Zhaoyi Song
Papers
2
Total Citations
8
H-Index
1
About
Zhaoyi Song is an emerging researcher specializing in multi-agent systems, reinforcement learning, and robotic path planning. Their work addresses one of the most demanding challenges in autonomous robotics: the Multi-Agent Path Finding (MAPF) problem, which involves coordinating large numbers of robots navigating complex environments simultaneously without collision or deadlock. Song's most notable contribution is the development of HELSA (Hierarchical Reinforcement Learning with Spatiotemporal Abstraction), a framework that leverages hierarchical reinforcement learning to enable scalable, fully decentralized solutions to large-scale MAPF problems. This work, accumulating 7 citations since its 2023 publication, introduced spatiotemporal abstraction as a means of managing the computational complexity that plagues traditional MAPF approaches. Building on this foundation, their 2025 follow-up applies a "divide and conquer" strategy to push scalability further, demonstrating a sustained commitment to solving real-world multi-robot coordination challenges. Song's research sits at the intersection of artificial intelligence and robotics, with direct implications for warehouse automation, autonomous vehicle fleets, and disaster response systems. Though early in their career, their focused and progressive body of work signals a promising trajectory in intelligent multi-agent systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2