Samuel Spetalnick
Papers
2
Total Citations
17
H-Index
2
About
Samuel Spetalnick is a leading researcher in energy-efficient edge computing, specializing in hardware accelerators for autonomous micro-robotics. His work focuses on integrating machine learning inference with embedded non-volatile memory, particularly resistive RAM (RRAM), to enable real-time perception and localization on power-constrained platforms. Spetalnick’s most notable contribution is the development of a 40nm VLIW edge accelerator featuring 5 MB of 0.256 pJ/bit embedded RRAM, designed specifically for bristle robot surveillance. This accelerator efficiently handles a dual workload: a neural network inference stack for perception and a state-space equation solver for localization, all within a compact, low-energy footprint. His 2024 ISSCC paper on this work has garnered 15 citations, highlighting its immediate impact on the field. By addressing the unique challenges of miniaturization and low-power actuation in bristle robots, Spetalnick’s research paves the way for autonomous surveillance systems that are both tiny and intelligent, pushing the boundaries of edge AI in robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2