Papers
2
Total Citations
22
H-Index
2
About
Hyochan An is a leading innovator in energy-efficient, domain-specific system-on-chip (SoC) design for autonomous micro-robotics and embedded vision. His research centers on enabling fully-on-chip intelligence for resource-constrained platforms, with key contributions in hybrid processing architectures and emerging memory integration. An’s most cited work introduces a flexible micro-robotic vision SoC fabricated in 22nm technology, achieving an impressive 3.5 TOPS/W efficiency. This design features a novel hybrid processing element (PE) that efficiently handles both convolutional neural network (CNN) and non-CNN vision tasks, paired with 2MB of embedded MRAM (eMRAM) for retentive, fully-on-chip weight storage—eliminating off-chip memory dependencies. His follow-up work, RoboVisio, extends this architecture specifically for autonomous navigation, demonstrating how domain-specific SoCs can deliver high efficiency and flexibility for real-time micro-robot vision. With over 20 combined citations for these foundational papers, An’s contributions are shaping the future of intelligent, low-power edge devices. His achievements represent a critical step toward practical, self-contained micro-robots capable of complex visual processing without cloud or external memory support.
Research Focus
Key Achievements
Top Papers
- 1
- 2