Nvidia has unveiled a new entry-level AI computer at GTC, the computer is called Jetson Nano which is made for developers, makers, and enthusiasts. It is a cheap computer comes for only $99, Nano is the latest in Nvidia’s line of Jetson embedded computing boards, used to provide brains for robots and other AI-powered devices.
Plug Nano into one of your devices and it will be able to handle a task like an object recognition and autonomous navigation without relying on cloud processing power. This kind of setup is known as edge computing because the data being processed from cameras and microphones never leaves the device. Therefore, the end result of Hardware is faster, more reliable and more secure.
The company claims that Jetson Nano features 128-core Maxwell-based GPU and quad-core ARM A57 processor able to deliver 472 gigaflops of processing power for neural networks, high-res sensors, and other robotics features while still consuming a miserly 5W. The AI computer supports many popular AI frameworks, including TensorFlow, PyTorch, Caffe, Keras, and MXNet. It has the usual ports and interfaces, including USB-A and B, Gigabit Ethernet, and support for microSD storage.
Nvidia also released a DIY project for advanced makers, it is an open source $250 autonomous robotics kit named JetBot. It consists of a Jetson Nano along with robot chassis, battery pack, and motors, allowing users to build their own self-driving robot.
“We expect a lot of the maker community that wants to get into AI, but has been unable to in the past, the Jetson Nano will allow them to do that,” Nvidia’s VP and GM of autonomous machines, Deepu Talla, told reporters at a briefing.
As we know this AI device priced lowest which makes it the cheapest device, but this is not unique as Intel, for example, sells its Neural Compute Stick for $79. Too, Google recently unveiled two similar devices under its Coral brand, a $150 devkit and $75 USB accelerator.