Memristor Technologies for Dynamic Vision Sensors: A Critical Assessment and Research Roadmap
For researchers in neuromorphic computing and edge-AI, this paper provides a critical assessment and roadmap, highlighting the gap between projected and demonstrated systems.
The paper surveys memristor-based dynamic vision sensors (DVS) for edge-AI, finding that half of six application domains rely on projections rather than fabricated hardware, with existing systems at Technology Readiness Levels 2-5. It identifies an integrated DVS-memristor system as the key open challenge.
Edge-AI deployment is bottlenecked by data-movement energy; pairing event-driven vision sensors with in-memory analog compute could lift that ceiling by orders of magnitude. Both technologies are individually mature; the framework distinguishing fabricated demonstrations from projected systems is missing. Of six application domains surveyed (robotics, autonomous vehicles, AR/VR, surveillance, medical imaging, IoT), half rest entirely on projection, and existing hardware sits at Technology Readiness Levels 2-5. This evidence-graded review applies a three-paradigm architectural taxonomy and benchmarks the gap against current digital neuromorphic alternatives. It identifies an end-to-end integrated DVS-memristor system as the field's open challenge, with testable accuracy and power targets.