Yao Jinyi

Papers

Total Citations

H-Index

About

Yao Jinyi is a pioneering researcher in multi-agent systems and robotic coordination, best known for foundational contributions to the RoboCup simulation domain. His work centers on enabling autonomous robots to plan and cooperate effectively under real-time constraints, using observation-based strategies and reinforcement learning. His most influential paper, "Global Planning from Local Eyeshot" (2002, 9 citations), introduced a novel framework for plan coordination in RoboCup simulation games, demonstrating how agents could achieve global objectives using only local perceptual data. This work laid the groundwork for decentralized decision-making in competitive multi-robot environments. Yao further advanced the field with "Technical Solutions of TsinghuAeolus for Robotic Soccer" (2004, 6 citations), which detailed the architectural and algorithmic innovations behind a championship-caliber robotic soccer team. His third key paper, "Multiple Rewards Fuzzy Reinforcement Learning Algorithm in RoboCup Environment" (2002, 5 citations), proposed the multi-reward fuzzy Q-learning algorithm (MRFQLA), a method designed to handle complex cooperation tasks in multi-agent systems. Though modest in citation counts, Yao’s research is highly regarded for its practical impact on autonomous coordination and learning in dynamic, adversarial settings—a cornerstone of modern multi-robot systems.