Quantized deep learning models on low-power edge devices for robotic systems
This work addresses efficient deep learning deployment on edge devices for robotic systems in agriculture, though it appears incremental.
The authors deployed a quantized deep neural network on a low-power edge device to infer motor movements for a suspended robot, achieving unspecified performance improvements for agricultural applications.
In this work, we present a quantized deep neural network deployed on a low-power edge device, inferring learned motor-movements of a suspended robot in a defined space. This serves as the fundamental building block for the original setup, a robotic system for farms or greenhouses aimed at a wide range of agricultural tasks. Deep learning on edge devices and its implications could have a substantial impact on farming systems in the developing world, leading not only to sustainable food production and income, but also increased data privacy and autonomy.