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 Feb 25, 2019

Delivery Schedule, Board Photos, GTC, and More

Deepwave Digital at GTC San Jose

If you plan to come to NVIDIA’s GPU Technology Conference in San Jose, CA from March 17-21, come by and see us. The Deepwave team will be in the vendor exhibit area March 19-21. Stop by if you want to chat about the AIR-T, deep learning, or just want to check out the product before yours ships. There will also be a number of technical presentations focused on deep learning applications for radio frequency systems, including a talk by Deepwave.

Manufacturing Has Begun!

We are excited to announce that we are kicking off the manufacturing run of the production model AIR-T this week! Bringing the first deep learning-centric software defined radio (SDR) from an idea to a commercial product has been a long and exciting engineering adventure. The AIR-T has a 12-layer PCB with over 1,300 components. On top of all that, we we want to supply our customers with a familiar and functional software interface for command, control, and operation of the platform. While we hope to get the AIR-T to our first backers sooner, our conservative estimate for final delivery is March 31. We would like to thank our supporters for their patience, generosity, and support.

Photographs of AIR-T

Here are some photographs that we took of the final production model of the AIR-T.

Much more to come, so stay tuned!

More Information on GR-Wavelearner Software

We have put together a presentation explaining how to use GR-Wavelearner to deploy neural networks on the AIR-T, which consists of three steps:

  1. Train - Using TensoFlow, MATLAB, Keras, Pytorch, or your favorite deep learning framework
  2. Optimize - Take your trained neural network and optimize it using TensorRT
  3. Deploy - Using GR-Wavelearner, GNU Radio, and the AIR-T

Check out the slides here for more details.

$205,212 raised

of $20,000 goal

1,026% 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: