Ruiyuan Fan

Beijing University of Technology, Institute of Art

Papers

Total Citations

H-Index

About

Ruiyuan Fan is a pioneering researcher in autonomous robot navigation, with a focus on enabling intelligent decision-making in unknown and hazardous environments. His work bridges reinforcement learning and bio-inspired neural architectures, most notably through the development of a Q-Learning algorithm integrated with a Dynamical Structure Neural Network for robot navigation, which has garnered 8 citations and laid the groundwork for adaptive, self-learning systems. Fan further advanced the field by proposing a hybrid A* and Q-Learning approach for search and rescue robots, introducing a bionic self-learning algorithm that leverages Growing Self-organizing Maps (GSOM) to construct topological cognitive maps of unknown terrains. This work, cited 4 times, demonstrates how heuristic search methods can be combined with reinforcement learning to improve navigation efficiency in critical, time-sensitive missions. Fan’s contributions are particularly notable for their practical impact on search and rescue operations, where robots must autonomously explore and navigate without prior environmental knowledge. His research continues to inspire new directions in adaptive robotics, reinforcement learning, and cognitive mapping, making him a key figure in the development of intelligent, autonomous systems for real-world applications.