Nvidia powers up drones, robots with Jetson TX1 board

The TX1 is roughly the size of a credit card, yet it can churn out 1 teraflop – a trillion floating point operations every second.

The Jetson TX1’s unique learning abilities are thanks to its graphics processing unit, or GPU, which is created to carry out the parallel processing necessary to undertake machine learning and deep neural networks, according to ARS Technica.

The TX1 should make it easy for hardware builders to experiment with AI-assisted robots, self-driving and autonomous navigation systems in vehicles and drones, and smart Internet of Things- devices. Well, actually it’s Nvidia’s Jetson TX1 module [pictured], created to allow drones to fly autonomously without the need for human operators, that has arrived.

“They will navigate on their own, recognize objects and faces, and become increasingly intelligent through machine learning”.

The Linux-powered module comes with its 1 teraflops of performance, 4-bit ARM A57 CPUs, 1GB Ethernet networking, 802.11 ac Wi-Fi and is under 10 watts.

Nvidia has introduced a new machine learning supercomputer called the Jetson TX1. The actual Jetson TX1 developer kit will include the Jetson TX1, a developer board and a 5MP camera.

As a result, the platform is capable of performing complex tasks such as recognizing images, processing conversational speech, or analyzing a room full of furniture and finding a path to navigate across it. Nvidia described the Jetson TX1’s machine learning abilities as “a groundbreaking technology that will give autonomous devices a giant leap in capability”. A discount will also be available for educational use, with the MA Institute of Technology already declaring it will base its robotics systems and science course around the module. These are primarily focused at capturing a greater portion of the machine learning market. Berkeley Design Technology president Jeff Bier said that developing for the TX1 felt more like PC development than typical embedded board development and praised Nvidia on the ease of installing system images and providing support for CUDA, making harnessing the power of the GPU much more simple. It will be priced at $599 in the U.S. ($299 for education customers) with shipping expected on 16 November.