Robots and drones require autonomous and smoother navigation capabilities, and the TX1 will help enable such capabilities, said Jesse Clayton, product manager at Nvidia.
Advertisement
The TX1 is more than three times faster than last year’s original Jetson board, which delivered 300 gigaflops of horsepower.
NVIDIA has unveiled a new mini supercomputer in the form of the Jetson TX1 module that measures just 50mm x 87mm in size and has been specifically created to bring artificial intelligence to the next generation of autonomous drones and robots.
“They will navigate on their own, recognize objects and faces, and become increasingly intelligent through machine learning”.
Nvidia’s Jetson TX1 offers 64-bit ARM cores and 256 Maxwel-class GPU cores in a tiny COM design, but you’ll pay for the privilege of its use.
The TX1 SDK is interesting because it is capable of pushing one teraflop where performance is concerned, it does this in just under 10 watts and comes with Linux installed. There’s onboard 802.11ac Wi-Fi and Bluetooth, wired gigabit Ethernet, and 16GB of eMMC storage for the bundled OS – Linux for Tegra (L4T), which is based on Canonical’s Ubuntu Linux. For essential maker-board style expansion and interfacing Nvidia has kitted out the Jetson TX1 board with 3x UART, 3x SPI, 4x I2C, 4x I2S, and GPIOs. Ground-breaking advances in machine learning have made it possible to use AI techniques to create smarter applications and services. The TX1 does not support Android. Karaman said MIT students will use XT1 boards’ embedded vision, stereo reconstruction and machine learning in research and technology projects.
The SDK is based on Nvidia’s CUDA parallel programming framework, and taps into technologies such as OpenCV, OpenVX and Nvidia’s VisionWorks for image recognition.
Advertisement
The developer board will be available starting on November 16 for $599 through online retailers like Amazon and Newegg. The Jetson TX1 module will become available early next year priced at $299 in bulk.
