Papers
5
Total Citations
77
H-Index
5
About
Jinsu Lee is a leading researcher in energy-efficient artificial intelligence hardware, specializing in processors for autonomous mobile robots and edge computing. His work focuses on enabling intelligent decision-making in battery-powered systems through ultra-low-power AI accelerators. Lee’s seminal contribution is the development of a 0.55V, 1.1mW artificial-intelligence processor with on-chip PVT (process, voltage, temperature) compensation, which demonstrated that complex AI functions like perception and cognition could be realized within the stringent power budgets of micro robots (25 citations). He further advanced the field with OmniDRL, a deep reinforcement learning processor achieving an impressive 29.3 TFLOPS/W through dual-mode weight compression and an on-chip sparse weight transposer (17 citations). Lee also designed the DSPU, a real-time depth signal processing unit for dense RGB-D data acquisition and 3D bounding box extraction in mobile platforms, operating at 281.6mW (16 citations). His notable achievement includes the BRAIN deep search engine, a low-power architecture tailored for autonomous robot navigation. With over 77 cumulative citations across his top works, Jinsu Lee’s innovations are pivotal for the next generation of autonomous systems, from delivery drones to augmented reality devices.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5BRAIN: A Low-Power Deep Search Engine for Autonomous Robots5 citations · 2017