@Adrian-Hidalgo I redesigned the mounting piece for the cameras, used new refocused cameras, and fixed some errors in my general camera extrinsics file (although I'm not sure that last one is related)

Hi @Anubhav ,

Docker should natively work on VOXL2... so the voxl-configure-docker-support shouldn't be used at all on VOXL2....

Should be able to use this directly: https://docs.docker.com/engine/install/ubuntu/

If VOXL2 isn't booting... you can reflash with the platform release, and please just don't run voxl-configure-docker-support (and we need to fix this script to not run on VOXL2.....)

To reflash:
https://docs.modalai.com/platform-releases/#install

@bendraper in other words, what factors/scripts affect the generation of that conf file?

Hi @jonathankampia,

After running voxl-mpa-to-ros, you should see the /tflite_data and /tflite topics created as they just mirror the existing pipe names from the tflite-server.

I am not sure what you are referencing with the tflite_detections topic, but if you could share the output of voxl-version, voxl-list-pipes, as well as a rostopic list with the two services running I can help debug.

Are the sensors mounted rigidly on the same plane, facing exactly the same direction?

Can you make sure they are both well in focus?

Hi @liftedsystems
I just saw this now.. sorry for our delays on this...
We respond better when you start a new thread because we ALL get notified of it internally ... Thread replies are on a "best effort" basis to check so we miss some.... but if you wish to do so, please just tag us using the "@" like you did to get Chad and we will see that at a higher level too, but new threads are always the best!
Thanks, and I hope Travis gave you the info you were hoping for!!

@Vinny Side note: I'm slicing off the little retention nubs on every DF13 connector I own today. I would suggest anyone planning on doing a lot of detachment-insertions consider this. I really don't think DF13's were ever meant for a lot of In-Out especially in awkward placements. Long live GH 1.25's..

@modaltb Sorry for the delay in replying.

apt-get install jq, worked and fixed the problem. I am about to update the system image.

Many thanks.

@Chad-Sweet any suggestion?

@Chad-Sweet I have used both dev as well stable packages

"name": "hires", "enabled": true, "frame_rate": 30, "type": "imx214", "camera_id": 2, "preview_width": 640, "preview_height": 480, "record_width": 1920, "record_height": 1080, "snapshot_width": 3840, "snapshot_height": 2160, "ae_mode": "isp"

In the camera configuration file type of camera is "imx214". Is it correct?

your image of the voa_pc_out point cloud shows that your voxl thinks the TOF is pointing out the top of the drone. This is confirmed by your extrinsics conf sensor rotation: [180 0 0] which translates to a sensor pointing straight up.

It is likely that driver is not supported. You may need to add it to the VOXL 2 PX4 build if you want to use the integrated flight controller. It may be easier to use an external flight controller if you want to use a broader set of inputs

https://docs.modalai.com/voxl-px4-developer-guide/

Resolved

Hi Dan,

We haven't tried this yet, and we don't have a pre-built solution that we can reference, but it should be doable.

PX4 on VOXL2 is setup mainly to use the DSP UART right now, which are setup for an ESC and a GNSS (GPS) unit. In theory, the gimbal driver would just need to use one of these ports, but I have a hunch there's some coding involved, and it would take over one of the two UART ports above which might not be OK for you.

We aren't doing this yet, but there are UARTs on the applications processor side that could be used via an add-on board for this use case likely.

So, to sum it up, doable, but not out of the box from our docs at this point.

@Vinny Thanks for your comments. Actually we have sent the block diagram to Chad for review. Once we have done the schematic, we will send to ModalAI for review.