@Nikos-Mavr You're welcome! And can you please start a new forum post for this new issue? Thanks!

@DronAlan Hi there, when the camera was rotated 180, you'll have stable take off behavior, but any XY movement would cause the drone to 'fly away' quickly.

Taking a step back with your concerns on physical mounts:

checking camera orientation:
a. bring up the front camera in portal: it should be upright orientation, e.g. top of the camera image should be from the top of the drone itself ("tops are aligned").

Since you are using qvio, only 1 camera is supported. Ensure in /etc/modalai/vio_cams.conf has tracking_down disabled, It's a safeguard if qvio is accidentally using that camera (would would lead to a orientation problem).

As for IMU, the voxl2 unit should have the USB-C port facing the bottom/ground side (and WiFi dongle on the top side). Let's force reset the imu calibration. If you run on the drone voxl-calibrate-imu and follow the directions, will reset the imu.

Let's check these items. If they all pass and still presents the orientation problem, then it's worth moving to the SDK1.6.3 to take advantage of the advanced config installer.

@Myles-Levine , if you are masking out 90% of down-facing camera, then it is probably useless any movement of the features will get it out of the unmasked region very easily and feature will be dropped.. It may hurt VIO as there may be features going in and out, only trackable for a few frames (just adds to the complexity).

You should try to move the down-facing camera to free up it's FOV or even have it facing slightly angled to the back of the drone..

Alex

@Alex-Kushleyev That’s very helpful if disabling regenerative braking is working as intended, then it sounds like that addresses the primary concern on our bench-supply side.

From the flight-controller dynamics side, we’d still generally prefer to keep braking enabled in the long run, but handling the FC tuning impact is something we’re comfortable with. The main blocker for us has been finding a clean way to absorb regenerative energy on the bench supply during decel events.

Given that regen disable appears to solve that issue, we’ll plan to proceed with controlled validation on our motor/prop combination while monitoring bus voltage during transients.

A couple follow-up questions:

list item Would you recommend exposing regenerative braking disable as a user parameter, or is this better handled as a custom firmware build for this application? list item Did you end up making any ESC tuning parameter changes when testing in this mode, especially for a lower-kV / larger-prop setup? If so, would you be willing to share those changes?

@Dan-Jennings I'm also guessing that the driver may not be detecting the hardware so is not able to get the data for the battery_status. Have you tried swapping some other hardware to see if the problem is associated with a particular unit?

@emarcphera @Eric-Katzfey thank you so much after upgrading to voxl-mainline im getting GPS readingScreenshot from 2026-02-28 01-45-10.png

@RyanH ,

Sometimes there is small pieces of random magnetic debris that gets stuck in the motor.

First, you could try using compressed air to clear out the motor.

Additionally, It could help to spin the motor up and down using voxl-esc command line tools a few times to clear it out (without prop is best, just for safety). Spinning the motor without prop a bunch of times could get the debris dislodged and actually broken up by the moving motor parts, so that the debris is no longer large enough to cause a problem. Reversing motor spin using voxl-esc test tools can help dislodge the debris (you can commend negative power/rpm).

You can find useful info regarding motor testing here : https://docs.modalai.com/voxl-escs/faq/

Alex

@bendraper
Hello,
I hope this quick clarification helps for warnings:

CMake Policy warnings: OV internally (external dir in the repo) still uses boost and references an older cmake version -- it's a harmless warning for devs (as you are building from scratch)

Yaml-cpp lib warnings: This is a third party dependency that gets compiled from scratch during the make/build process. We use C++ 17 but the library is based on an older C++ version; nevertheless, it compiles fine on C++ 17 with minor warnings. -- it's a harmless warning

TrackOCL warning: ModalFlow is a core library written in C++ 17 that allows function call usage as done in TrackOCL, i.e., the narrowing conversion is harmless in this case.

That being said, we are actively working on the dev branch, so all flight--impacting warnings are hopefully caught early. We currently have no flight-impacting warnings/bugs identified, but if you found one warning/bug that caught your attention, please feel free to share.

All the best,
ZBFT

@restore There are a few examples of code that listens for Mavlink messages in our SDK. For example, in voxl-mpa-tools, take a look at the source code for voxl-inspect-mavlink.c. https://gitlab.com/voxl-public/voxl-sdk/utilities/voxl-mpa-tools/-/blob/master/tools/voxl-inspect-mavlink.c?ref_type=heads

Probably would be a good idea to run voxl-inspect-mavlink on the mavlink_onboard and mavlink_to_gcs pipes to see which one has the desired Mavlink message in it. Then create your own application that listens for the Mavlink message on that pipe.

@Alex-Kushleyev The Alfa Network AWU2036

@qubotics-admin First you need to determine the version of PX4 running. With ssh or adb you can run the following at the command line: px4-ver all. You will see PX4 version and Vendor version. So, for example, for px4 version 1.14.0 and vendor version 8.134.3 then you would checkout the tag v1.14.0-8.134.3-dev from the repo to see that commit.

@ndwe Whether you use a VOXL or Jetson as a companion computer shouldn't make any difference unless you want to use the VOXL SDK. The version you run is totally up to you. If our v1.14.0 based version works for you then use it. We do plan to transition to v1.17.x in the near future. I don't think the issues you are seeing are related to something specific in the flight core v2 hardware setup. I would think that if you swapped it out for some other brand you would see the same issue. I would ask on the PX4 forums to see if others have experienced the same issues.

Hi @Alex-Kushleyev, sorry for the late reaction, it took some time before i could update to the new SDK (1.6). the system now works normally with the resolution 2704x1540, and downscaled to 1920x1080 for the MISP pipeline. Thanks for the help!

@Piyush-Singh , can you please provide more details

how exactly all cameras are connected to VOXL2 mini (including interposers, flexes), etc. A diagram would help a lot which kernel variant are you running on your voxl2 mini (2.0.0 or 2.0.2).

Are all the other cameras working if you disable the TOF sensor in the camera server config?

Alex

@cbay voxl-fpv-px4 is based on voxl-px4 but has some custom tuning code / parameters for our fpv drones that isn't in voxl-px4. So, it's kind of a superset. But there isn't anything related to low level i2c drivers so I have no idea how that could be causing this issue.

@Jetson-Nano , since we currently have no plans to do the MIPI integration of this sensor, you always have the option to use USB connection and voxl-uvc-server to publish images via MPA. You would need to check if the sensor supports the standard UVC interface and try it out...

Alex

@Alex-Kushleyev Thank you for the hint. We have fixed the issue by changing the resolution to 2704x1540 in the voxl-camera-server.conf. Now, the actual DFOV is 150°.

Hi @Vinny

Thank you for your reply! That's good news:)
We are looking forward to it!

@colombe-ai , please see https://forum.modalai.com/topic/5116/gnss-emi-mitigation-guidelines

@Alex-Kushleyev Thanks Alex, very helpful!