Myung Seok Shim
Papers
2
Total Citations
30
H-Index
2
About
Myung Seok Shim is a leading researcher at the intersection of biologically inspired robotics and deep learning, with a primary focus on autonomous navigation and sensor fusion. His most impactful work, "Biologically inspired reinforcement learning for mobile robot collision avoidance" (2017, 28 citations), pioneered the integration of spiking neural networks (SNNs) with reinforcement learning—specifically Q-learning—to enable more efficient and adaptive collision avoidance in mobile robots. This approach mimics biological neural processing to improve real-time decision-making in dynamic environments, a critical capability for autonomous vehicles and robotics. Shim further advanced the field with his work on "Optimized Gated Deep Learning Architectures for Sensor Fusion" (2018), where he developed novel neural network structures that intelligently combine data from multiple sensors, enhancing robustness in applications like autonomous driving. His contributions bridge the gap between neuromorphic computing and practical robotics, offering energy-efficient solutions that learn from experience. By demonstrating how biologically plausible models can outperform traditional methods in reactive control tasks, Shim has established himself as a key innovator in creating safer, more intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Optimized Gated Deep Learning Architectures for Sensor Fusion2 citations · 2018