Artificial Intelligence Radio - Transceiver (AIR-T)

by Deepwave Digital

A high-performance SDR seamlessly integrated with state-of-the-art deep learning hardware

View all updates Nov 11, 2018

Testing Prototypes and Announcing GR-Wavelearner

The AIR-T prototypes have arrived and are undergoing testing, delivery of production units has been pushed to January, and we have a new deep learning tool for GNU Radio.

AIR-T Prototypes Have Arrived!

The AIR-T prototypes are here and we’ve been putting them through tests! Our contract manufacturer has done an excellent job at making sure the AIR-T meets our specifications. We still have a few weeks of testing and then there will be some slight changes based on our findings. As things sometimes go with manufacturing a complex piece of hardware like the AIR-T, we are a bit behind schedule. Because of this and the upcoming holidays, our updated estimate for shipping is now January 15, 2019. In the meantime, we would like to share some AIR-T eye candy with you.

We’ll keep you posted on the progress of the testing and production.

GR-Wavelearner: An Open Source Deep Learning Tool for GNU Radio

GNU Radio has become synonymous with the rapid prototyping of software defined radio (SDR) solutions. GNU Radio has simplified development for everyone, from beginners just starting to explore the radio frequency (RF) spectrum, to seasoned digital signal processing (DSP) engineers. While GNU Radio has a huge library of DSP functionality, there are limited resources for deploying deep learning algorithms. This is why the Deepwave team has created GR-Waveleaner.

GR-Wavelearner is an out of tree (OOT) module for GNU Radio that interfaces to NVIDIA’s TensorRT deep learning binaries from a GNU Radio flowgraph. TensorRT optimizes deep learning networks for inference operations on an NVIDIA graphics processing units (GPU). We’ve tested GR-Wavelearner on the AIR-T, laptops, and NVIDIA Tesla GPUs.

Download GR-Wavelearner here

The comprehensive README file will help you get started, and, best of all, we actually provide you with a trained convolutional neural network (CNN) that classifies signals based on deep learning! You can use the trained CNN to learn the ropes or adapt it to your own application.

We’ve put a lot of effort into making GR-Wavelearner a great tool and we even got our friends at NVIDIA to take it for a test drive with their Docker environment. We think it is a great way to deploy deep learning for wireless technology, but we really want to know what you think.

Example Flow Graph of Deep Learning Classifier

Thanks for your support,
The Deepwave Team

$199,313 raised

of $20,000 goal

996% Funded! Order Below

Product Choices


Air-T With Enclosure

The AIR-T is the first platform that enables out-of-the-box machine learning wireless systems. Simply port current GNURadio or code directly in Python to access the radio frequency spectrum. Includes, AIR-T board, four MCX-to-SMA cables, getting started tutorial, and power supply. The Air-T enclosure is expertly constructed from aluminum to produce a polished, elegant, and sleek metallic silver finish. It measures 192 x 182 x 79 mm (7.5 x 7.2 3.1 inches) and the power button illuminates blue when they system is on. All RF ports are brought to the front of the enclosure for ease of use and all computer peripherals connections are brought to the rear.


Deepwave Digital

We are a dedicated team of radio frequency and wireless industry experts with over fifty years of combined experience providing digital signal processing solutions to the commercial and defense industries. We understand both the technical capabilities as well as the limitations of these technologies, leading us to develop novel hardware and software solutions to combine the fields of artificial intelligence and signal processing.

John Ferguson

Steven Kline

Peter Witkowski

Steve Lisi

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects: