Hoiio Kong
Papers
2
Total Citations
7
H-Index
2
About
Hoiio Kong is a rising researcher at the forefront of neuromorphic computing and robotic tactile perception, pioneering the integration of event-based sensing with probabilistic spiking neural networks (SNNs). Their work addresses a critical challenge in industrial robotics: enabling fast, accurate, and energy-efficient tactile recognition for tasks like snap-fit peg-in-hole assembly, particularly for fragile 3C electronics components. Kong’s most-cited paper, “Evetac Meets Sparse Probabilistic Spiking Neural Network: Enhancing Snap-Fit Recognition Efficiency and Performance” (2025, 4 citations), demonstrates how event-based optical sensors like Evetac, combined with sparse probabilistic SNNs, achieve high sparsity and sensitivity for real-time tactile feedback. Their subsequent work, “Probabilistic Spiking Neural Network for Robotic Tactile Continual Learning” (2024, 3 citations), tackles the problem of distribution shift in tactile data as robots encounter new tasks—a key limitation of traditional artificial neural networks. By introducing probabilistic SNNs, Kong enables robots to learn continuously without catastrophic forgetting, a breakthrough for adaptive automation. Though early in their career, Kong’s contributions are already shaping the future of neuromorphic tactile systems, promising more robust, lifelong learning for autonomous robots in manufacturing and beyond.
Research Focus
Key Achievements
Top Papers
- 1
- 2