Minglan Fu

Papers

Total Citations

H-Index

About

Minglan Fu’s research lies at the intersection of multi-robot systems, game theory, and cooperative artificial intelligence, with a particular focus on designing algorithms that ensure robust system performance even when individual agents act in self-interest. In their notable work “Coalitional Skill Games for Self-Interested Robots with SVO” (2018), Fu addresses a critical challenge in robotics: how to maintain high overall system revenue when robots cannot communicate and prioritize their own performance. By modeling interactions through coalitional skill games and incorporating Social Value Orientation (SVO), Fu proposes a novel algorithm that aligns individual incentives with collective goals, enabling effective task allocation without direct communication. This work, cited 3 times, provides foundational insights for decentralized coordination in real-world applications like search-and-rescue or warehouse automation. Fu’s contributions are particularly valuable for researchers exploring trustless multi-agent systems, offering a principled approach to balancing individual rationality with system-level efficiency. Their work continues to inspire further studies in cooperative robotics and mechanism design.