Nvidia Jetson TK1

 In News

BG repair bot
I have been closely watching news of a new embedded platform that has finally come out. The Jetson TK1 is a huge step forward in my mind towards home robots. This board if you have not seen it is a tiny motherboard/system on a board. It contains a radical new processor developed by Nvidia its name is the Tegra K1 SOC. Containing both a ARM proc and a Kepler GPU with 192 CUDA cores.

So you may ask what does this mean for robotics. Well you can throw a heavy duty Intel I7 on a robot chassis and wire it in. This would indeed be able to run vision processing and the robot but of course there are two problems with this method. One is the size it would take up a lot of room on a chassis and the second being power usage. A I7 Intel processor would drain the on board battery source in under a hour. That is just the processors power usage! This is where the Jetson is a true super computer on a board. Running a K1 parallel processor capable of over 300 GFLOP/s of 32-bit floating point computation. All this processing power is on a 5 inch by 5 inch board that consumes under 10 watts during most high video processing loads. Here is a link with a nice table of power usage while running computer vision. Link

This kind of performance vs power usage is just outstanding. It will allow many more embedded consumer level robotics to be released to the home. The home care robot of the future will be based on massive parallel processing. I plan on getting one next week to use on my new pi robot. Its sad really its so good I just cant pass it up. If you are interested in this as well check it out at they retail for  192 dollars at the time of this writing. I will be updating the (Pi)Nvidia Jetson robot as I go. Make sure to check back regularly to see the development and code.

https://developer.nvidia.com/jetson-tk1#source=pr

Here is also a great link to a wiki on setup and a few tutorials using OpenCV and running on batteries. Link

$_3

 

Full specs below

  • Tegra K1 SOC
    • Kepler GPU with 192 CUDA cores
    • 4-Plus-1 quad-core ARM Cortex A15 CPU
  • 2 GB x16 memory with 64 bit width
  • 16 GB 4.51 eMMC memory
  • 1 Half mini-PCIE slot
  • 1 Full size SD/MMC connector
  • 1 Full-size HDMI port
  • 1 USB 2.0 port, micro AB
  • 1 USB 3.0 port, A
  • 1 RS232 serial port
  • 1 ALC5639 Realtek Audio codec with Mic in and Line out
  • 1 RTL8111GS Realtek GigE LAN
  • 1 SATA data port
  • SPI 4MByte boot flash
Recent Posts
Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text. captcha txt
0

Start typing and press Enter to search