@jbhines929 No problem, thanks for the patience!

@goswamid , Yes we do sell those parts. Please contact us via online form. https://www.modalai.com/pages/contact-us The part number you will need is M10000524 Alex

@ashwin I don't have the info either but it's similar to VOXL2's weight which is 16g

Hello, @Stefan-Amundarain , Let's try to narrow this down. Can you reproduce the issue without flying? When the issue occurs, does the camera server restart completely, or you only lose hires camera feed. I suggest running the test on the bench with voxl-camera-server running in foreground so you can easily see what's happening in real time. Please try to reproduce on the bench all 3 cameras (hires, tracking, TOF) working with your Ark Flow board working as well, then you can just move the platform by hand, if needed, to cause the camera failure and investigate what: voxl-camera-server outputs output of dmesg We can go from there. Also, can you please provide details how the ARK Flow is actually connected to VOXL2 (electrically) and also confirm that the issue does not happen at all without ARK Flow plugged in? Also, using voxl-portal should not cause the camera server or the portal backend to get bogged down if your image is reasonable size (not full 4k image), but a small 720p is just fine. You could view the 3 camera streams thru voxl portal during the test or just have the voxl-inspect-cam tool running and inspecting just the streams that you want (you can provide the streams to inspect as arguments to the tool, such as voxl-inspect-cam hires tracking_down tof_depth, etc. Either voxl-portal or voxl-inspect-cam should properly use the camera pipeline with all camera streaming, so that you can catch the fault. Alex

@shivam-rana , if you have a few wifi adapters which are currently not detected by VOXL2, if you plug into a standard Linux machine and if they are detected, you should check with chipset is used on those adapters and we can see if that's available (but not currently compiled) option for the VOXL2 kernel. We can add some documentation to help you build your own test kernel with enabled module and see if that works. The VOXL2 kernel build guide is here : https://docs.modalai.com/voxl2-kernel-build-guide/ but it does not explicitly state how to make modifications to enable additional components. For those folks who have built kernels before, this may be easy to do, but for the first time it could be very difficult to do the right thing, but the change could be very small (one line). So we can see if it's possible to enable the driver that you need, but there would be no guarantees about functionality, since it would be untested (by us). Alex

Hello @Nathan-Raras and @Nathan-Raras , I don't see any Qualcomm device with running "lsusb". I also have confirmed that the USB-C cable is able to access another VOXL device. So I have submitted the RMA [image: 1748968811422-d45c5737-8bf3-4c8b-9e7d-851acbfe82a8-image.png] Please let me know if any questions or suggestions. Thank you very much for supporting.

@Tyler-Scott We recommend users to run linux natively as it can be tough to get USB devices to pass to WSL correctly.

You may also be able to resolve your issue by switching to voxl-cross:4.0 docker image, which was recently released.

@Alex-Kushleyev this is exactly what I need. Thanks! I was able to reconfigure voxl-tflite-server to use the new cropped image data.

@Moderator ok thanks, do you know if VOXL2 can do multiple drone communication ? seems cant find this on VOXL website?

@Alex-Kushleyev thank you! It works now.

@jonathankampia , yes IMX412 is supported on VOXL2 Mini J6 (either upper or lower). You can connect any two cameras to VOXL2 mini J6 using M0135 (double) or M0076 (single) adapter or for coax camera versions you can use M0155 (single) adapter. You would need to copy the correct sensormodule(s) to /usr/lib/camera/. see the following doc for help : https://docs.modalai.com/configure-cameras/#connect-a-new-camera Let me know if you need more details. Alex

@Tyler-Scott The voxl-streamer application streams video via RTSP https://docs.modalai.com/voxl-streamer/

Hi @KnightHawk06. If you're looking for all the data stored in the ai_detection_t struct we've done it in the past by opening up a libmodal pipe to the tflite detection path defined like this: #define TFLITE_DETECTION_PATH (MODAL_PIPE_DEFAULT_BASE_DIR "tflite_data/") Let me know if that suits your needs and if you need help opening the pipe.

@ashwin Unfortunately, Qualcomm does not allow others to distribute the Hexagon SDK. It has to come directly from them.