Mengwen Yuan
Papers
2
Total Citations
12
H-Index
2
About
Mengwen Yuan is a pioneering researcher at the intersection of neuromorphic computing and autonomous robotics, specializing in spiking neural networks (SNNs) and reinforcement learning for real-time navigation. Her work addresses critical challenges in mapless navigation, where robots must operate without pre-built environmental maps, and collision avoidance among dynamic, decision-making agents. Yuan’s most cited paper (2023, 9 citations) introduces a spiking reinforcement learning framework with memory ability, enabling efficient navigation in partially observable environments—a significant leap over traditional deep reinforcement learning approaches. Her subsequent work, CASRL (2024, 3 citations), extends this to multi-agent settings, developing energy-efficient collision avoidance policies that are crucial for resource-constrained mobile robots. By leveraging the biological plausibility and low-power advantages of SNNs, Yuan’s research bridges the gap between theoretical neuromorphic computing and practical robotics. Her contributions are particularly impactful for autonomous systems operating in dynamic, real-world scenarios, offering a path toward more intelligent, energy-aware robotic navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2