Topics created by david devassy

Thanks for the wonderful support from team modal AI. Here is the solution which they have shared with me, which is tested and working 100%.

Please download the attached file

file:
Download this

Move into the ufs sub directory of that release ^:
cd 2024-02-09-1.7.4-M0054-2/ufs

Slide the SW2 switch to ON to be in QDL mode
Plug in power and USB

Run:

sudo qdl --debug --storage ufs --include . prog_firehose_ddr.elf rawprogram_unsparse0.xml rawprogram1.xml rawprogram2.xml rawprogram3.xml rawprogram4.xml rawprogram5.xml patch0.xml patch1.xml patch2.xml patch3.xml patch4.xml patch5.xml

@david-devassy I'd recommend sending in an RMA: https://www.modalai.com/pages/rma and we'll get things sorted

@modaltb Hi thanks for the update. I have used the file which is shared by modal AI team through email and it worked 100%
Here is the file

https://storage.googleapis.com/modalai_public/qdl/2024-02-09-1.7.4-M0054-2.zip

Thanks again.

@david-devassy Have you been following the documentation here: https://docs.modalai.com/voxl-mapper/#voxl-mapper?

@tom
I have a new issue

Since yesterday, when I turned on the Starling drone, it just sits there. It's not getting armed. When I checked for ADB shell, it's not getting connected, and an error comes up saying no devices found. When I checked the forum, it said it might be bricked due to some file loss. We followed the unbrick tutorial, and after successful flashing of the latest QDL M0054.14.1a-flat-v3, the device is showing up as Qualcomm bulk something. However, ADB still isn't getting connected.
Please note that I am unable to enter adb shell and fast boot mode .

For unbrick I followed this
https://docs.modalai.com/voxl2-unbricking

@david-devassy

Hey David,

We do support deep learning inference on VOXL2! You can check out this page on our docs to read more about our deep learning capabilities. Out of the box our YoloV5 model gets around 30 frames per second. You also mention object avoidance and SLAM using path prediction. We have our own implementation of Visual Object Avoidance (VOA) which you can read about here.

You could certainly create custom implementations of both of these on VOXL! However I want to highlight that our code for both of the above is C/C++ and not in Python for speed reasons. I can't give you a reasonable estimate about Python performance but it would likely be slower.

Hope this helps! Let me know if you have any other questions.

Thomas Patton
thomas.patton@modalai.com