NEW Releasing: Grove AI HAT for Edge Computing and Look forward to your ideas!

Wow, looking cool! Hoping to see an accelerometer in the next revision and want to try it out soon.

I think it’s a good idea to add a connector for a battery pack, not to power the board with the battery only but to have an UPS for short power failure. It could be very useful to prevent data corruption.


Is there a release schedule for the revisions posted (for easy lookup) and order placement?


Hi Guys,

Thanks for all the wonderful ideas! Here is an update about things we are going to add to the next version.

  1. There AI HAT can power Raspberry Pi directly. Just use the onboard switch to switch power mode.
  2. There will be a microphone on board, the same microphone as the Sipeed 6+1 micarray.
  3. There will be an ADXL345, 3-Axis Accelerometer on board. We choose this one because there is already a Grove version of the sensor, the software is ready, easier to get a sample, and also lower cost.
  4. There will be a user button, and the boot LED can be used as user LED.
  5. The 40-Pin interface will be changed to SMT female header.
  6. The JTAG package will be smaller.

    We will finish the layout in a week, and get samples of the second version in the week of 22-Apr. If everything goes well, we will do pre-order in early May.

    Welcome to more ideas about how to using Grove with this HAT~

Hi baqwas,

We will finish the layout in a week, and get samples of the second version in the week of 22-Apr. If everything goes well, we will do pre-order in early May. Thank you~

This processor has an amazing APU ( audio processing unit ) that is capable of handling ( 8 ) 192 khz audio streams with hardware accelerated FWT processing. It would be a shame not to have a way to access those features via I2S. It would make an amazing engine for processing high-end audio, especially in combination with the Pi.

Please consider adding a camera that is ideal for future machine vision applications. At the moment Pregius Gen 3 Global Shutter CMOS is the my favorite. :slight_smile:

<LINK_TEXT text=“ … egius.html”></LINK_TEXT>

What do you expect from a good machine vision camera?

  • Accurate color reproduction
  • No chromatic aberration
  • Good low light performance
  • Interchangeable lens with mount system
  • High frame rate upto 120 fps
  • Ability to access and change the parameters of the camera settings (white balance etc)

    For conservation projects, the embedded vision camera need specific requirements.

    Camera with IR cut filter / IR-white-red flash /star light camera are ideal.

Indeed. And thanks for precvious feedback in this forum, we added an on-board microphone, and we have also breaked out I2S of the processpr to Raspberry Pi 40-Pin connector.

We will have a beginner kit for this Grove AI HAT soon and will include a camera in the kit. The idea is to include the camera that is being used by those Sipeed boards because it is cost-effective and can handle basic tasks. The Sony cameras can be great accessories to be purchased separately for higher level usage.


Good progress.

What about connector for external 6 Mic Array that’s already available for Maix, is it already there? Would be great to have it.

An update: Face Recognition Demo using Grove AI HAT for Edge Computing and Raspberry Pi

<LINK_TEXT text=“ … -pi-3e100f”></LINK_TEXT>

Artificial intelligence technology has been applied in various fields. Grove AI HAT for Edge Computing is a surprising news .And l want to share some discussions about AI : <LINK_TEXT text=“ … -of-things”></LINK_TEXT>

I don’t know if it will work for anyone else. I put this together yesterday.

It’s based on the native toolchain, so it may need some libraries installed as per the Kendryte-gnu-toolchain installation instructions. Or it may not work at all for others.

I have used it on my RPi3 and Jetson nano so far to build, upload and run some example sketches.

Well explained…

The idea is to distribute the data storage and intelligence in … Disclaimer: SeeedStudio has contacted me to review the Grove AI Hat for Edge Computing. … Hardware is actually evolving so quickly that we can see small .

We are going to release two versions, one based on the Sipeed MAIX-I with WiFi and another without. Both can work as a Raspberry Pi HAT, or work by themselves. The basic function and features are confirmed and listed here. But we are open to suggestions from the community about how to make this product.

You could add LAN controller f.ex.ENC28J60 or W5500 instead of wifi.

Also fpc for 16bit and 24bit LCDs

Is there a launch (i.e. general availability) date for the SKU?


Thanks for the inspiration, a 3-axis accelerometer sensor included at the board is sincerely extra convenient than using Grove. Will try and find a cost-powerful one in order that not including too much cost just like this for our customers, do you’ve got any recommendation for the 3-Axis accelerometer sensor?