Xinliang Li
Papers
1
Total Citations
14
H-Index
1
About
Xinliang Li is a pioneering researcher at the intersection of artificial intelligence, multi-agent systems, and resilient robotics. His work fundamentally addresses a critical gap in real-world deployment: the fragility of multi-robot coordination under unpredictable conditions like agent failures or communication disruptions. Li’s most impactful contribution is the development of a graph neural network-based multi-agent reinforcement learning framework, which enables distributed systems to dynamically adapt and maintain coordination even when individual agents are lost or network links are severed. This approach, detailed in his highly cited 2024 paper (14 citations), represents a paradigm shift from brittle, centralized control to robust, decentralized resilience. By modeling robot teams as evolving graphs, Li’s method allows each agent to leverage local information and learned policies to collectively reorganize, ensuring mission continuity in field robotics and other challenging environments. His work is not only theoretically novel but practically vital for autonomous search-and-rescue, exploration, and defense applications, establishing him as a leading voice in creating truly resilient, real-world multi-robot systems.
Research Focus
Key Achievements
Top Papers
- 1