Analog-to-Decision Classifier (A2DC)

Abstract

The Analog-to-Decision Classifier (A2DC) program will increase automated classification capabilities at the edge and simultaneously reduce the size, weight, and power (SWaP) needs of edge platforms. Currently, sensor outputs are digitized at the edge, which consumes SWaP and limits capabilities of edge platforms, but are then transmitted for processing at the command center. A2DC aims to skip or delay the digitization step and implement analog inferencing and compression techniques directly on the analog sensor data at the edge. A2DC objectives are to enable 1000-fold reduction on data transmission bandwidth required to communicate results for follow-on processing, and 100-fold reduction on SWaP for classification and processing of sensor data. A2DC will enable edge processing for missions that collect large amounts of sensor data, such as hyper spectral imaging for unmanned aerial systems.

Document Details

Document Type
Accomplishment
Publication Date
Oct 01, 2024
Source ID
f23675e17ae4966098100f6ae6788783

Tags

Readers

  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Computer Vision.
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • Autonomy

Related Documents