Donggyu Sim
Papers
1
Total Citations
5
H-Index
1
About
Donggyu Sim is a researcher at the forefront of neuromorphic computing and intelligent robotic control, with a particular focus on integrating biologically inspired spiking neural networks (SNNs) into reinforcement learning frameworks. His most notable contribution is the pioneering application of SNN-based twin delayed deep deterministic policy gradient (TD3) algorithms for 3D robotic arm manipulation, a breakthrough that bridges the gap between energy-efficient neural computation and complex real-world control tasks. This work, published in 2025 and already garnering 5 citations, represents the first successful demonstration of SNN-driven TD3 in robotics, offering a path toward more efficient and adaptive autonomous systems. Sim’s research addresses critical challenges in robotic dexterity, leveraging the temporal dynamics of spiking neurons to enhance learning stability and precision. His contributions are particularly significant for advancing low-power, real-time robotic applications, positioning him as an emerging leader in the intersection of computational neuroscience and robotics engineering.
Research Focus
Key Achievements
Top Papers
- 1