<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Feature Requests]]></title><description><![CDATA[Do you have a great idea for our products you would like to see implemented?]]></description><link>https://forum.modalai.com/category/29</link><generator>RSS for Node</generator><lastBuildDate>Fri, 17 Jul 2026 07:16:29 GMT</lastBuildDate><atom:link href="https://forum.modalai.com/category/29.rss" rel="self" type="application/rss+xml"/><pubDate>Tue, 07 Jul 2026 13:39:14 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Architectural review request: VOXL 2 for high-altitude VIO and encrypted RTSP routing]]></title><link>https://forum.modalai.com/topic/5310/architectural-review-request-voxl-2-for-high-altitude-vio-and-encrypted-rtsp-routing</link><guid isPermaLink="true">https://forum.modalai.com/topic/5310/architectural-review-request-voxl-2-for-high-altitude-vio-and-encrypted-rtsp-routing</guid><pubDate>Tue, 07 Jul 2026 13:39:14 GMT</pubDate></item><item><title><![CDATA[evaluating navigation technologies for UAV]]></title><link>https://forum.modalai.com/topic/5266/evaluating-navigation-technologies-for-uav</link><guid isPermaLink="true">https://forum.modalai.com/topic/5266/evaluating-navigation-technologies-for-uav</guid><pubDate>Mon, 15 Jun 2026 21:11:36 GMT</pubDate></item><item><title><![CDATA[voxl-send-command exit status implementation request]]></title><description><![CDATA[@jameskuesel Thanks! Merged
]]></description><link>https://forum.modalai.com/topic/5058/voxl-send-command-exit-status-implementation-request</link><guid isPermaLink="true">https://forum.modalai.com/topic/5058/voxl-send-command-exit-status-implementation-request</guid><dc:creator><![CDATA[Eric Katzfey]]></dc:creator><pubDate>Wed, 11 Feb 2026 16:11:18 GMT</pubDate></item><item><title><![CDATA[IMX664 Sync feature]]></title><description><![CDATA[@Richa . thanks for the details, got it it.
I will need to test the master / slave mode. Is your plan to have one IMX664 generate the sync signal (master) and the other(s) IMX664 being slaves? or all slaves?
I should be able to give it a quick test this week. The change would involve setting several additional registers in the camera configuration, which would mean a change in the sensormodule driver for the camera. we can figure this out after i verify the functionality.
Alex
]]></description><link>https://forum.modalai.com/topic/5028/imx664-sync-feature</link><guid isPermaLink="true">https://forum.modalai.com/topic/5028/imx664-sync-feature</guid><dc:creator><![CDATA[Alex Kushleyev]]></dc:creator><pubDate>Mon, 02 Feb 2026 09:36:36 GMT</pubDate></item><item><title><![CDATA[Voxl 3]]></title><description><![CDATA[Hi @Nate-The-great
Please do not delay any of your efforts or programs in anticipation of a VOXL 3 platform.
Our development roadmap is company confidential, but you can imagine we are working on many new and exciting things. One of the goals we have is to minimize disruptions should someone wish to "upgrade" platforms in the future. Similar to how we transitioned from VOXL to VOXL 2 by keeping mounting patterns the same, expansion compatibility (J13 -&gt; J3), and plug-in board and sensor compatibility (M0048, M0030, M0084 &amp; M0135 Camera adapters, etc), we would mimic that approach, but strive to make it even more seamless than before.
Therefore, there is very little to no risk to your system if you start developing on VOXL 2 today.
Hope that helped.
]]></description><link>https://forum.modalai.com/topic/4585/voxl-3</link><guid isPermaLink="true">https://forum.modalai.com/topic/4585/voxl-3</guid><dc:creator><![CDATA[Vinny]]></dc:creator><pubDate>Fri, 11 Jul 2025 01:16:34 GMT</pubDate></item><item><title><![CDATA[Clarification on R&#x2F;C System Frequency and Power Settings]]></title><description><![CDATA[@Eric-Katzfey Yes. This is regarding the Starling 2 Max GPS-denied Development Drone.
]]></description><link>https://forum.modalai.com/topic/4316/clarification-on-r-c-system-frequency-and-power-settings</link><guid isPermaLink="true">https://forum.modalai.com/topic/4316/clarification-on-r-c-system-frequency-and-power-settings</guid><dc:creator><![CDATA[Xavier_Team]]></dc:creator><pubDate>Fri, 04 Apr 2025 02:21:53 GMT</pubDate></item><item><title><![CDATA[Reccommendations]]></title><description><![CDATA[Hello @Kiran , the only TOF sensor that we currently sell is the following:
https://www.modalai.com/products/m0178?variant=48528287793456
https://docs.modalai.com/M0178/
In terms of identifying unique features of individuals, you will have you decide whether this works for you. Here is a typical output of the this TOF sensor looking at a person. This is a depth image, but a point cloud output (for each frame) is also available. In order to build a map, you would need to use some mapper software (we provide a reference such as https://docs.modalai.com/voxl-mapper/). However you would need to be familiar with mapping algorithm(s) and learn how the software components work in order to get mapping to work well and tune it for your application.
[image: 1744216152094-9b4bee44-2643-4aed-a20f-4ec2592af56b-image.png]
Alex
]]></description><link>https://forum.modalai.com/topic/4311/reccommendations</link><guid isPermaLink="true">https://forum.modalai.com/topic/4311/reccommendations</guid><dc:creator><![CDATA[Alex Kushleyev]]></dc:creator><pubDate>Thu, 03 Apr 2025 03:24:31 GMT</pubDate></item><item><title><![CDATA[Support Photo&#x2F;Video Capture via RC Switch]]></title><description><![CDATA[@JP-Drone said in Support Photo/Video Capture via RC Switch:

MAV_CMD_IMAGE_START_CAPTURE

How are you handling the mavlink camera protocol exchange within voxl-px4? I know that there is the ability to forward commands to the GCS if using mission commands (but not manually flipping an RC switch).
Alternatively when using a joystick you can map a button to image capture: https://docs.px4.io/v1.15/en/camera/mavlink_v2_camera.html#manual-controllers
Currently the mavcam manager fully implements the camera protocol to send the ack for the incoming mavlink commands. It also handles the capture and video stream status (satisfies the mavlink camera protocol).
My only issue with implementing this is that the upstream voxl-px4 will not be camera protocol compliant and thus we are bypassing the entire protocol just to get camera image capture from the autopilot instead of the GCS (which also implements the same camera protocol). If you have a way to implement the protocol (even a stripped down version of it) please send a link so I can look at the code.
]]></description><link>https://forum.modalai.com/topic/4117/support-photo-video-capture-via-rc-switch</link><guid isPermaLink="true">https://forum.modalai.com/topic/4117/support-photo-video-capture-via-rc-switch</guid><dc:creator><![CDATA[brahim]]></dc:creator><pubDate>Fri, 24 Jan 2025 06:08:48 GMT</pubDate></item><item><title><![CDATA[Multiagent RTSP Stream Support for QGC PX4 (VOXL2 SDK 1.3.3)]]></title><description><![CDATA[@Zachary-Lowell-0 Perfect, thanks! I'll try it when I get some time next week.
]]></description><link>https://forum.modalai.com/topic/3818/multiagent-rtsp-stream-support-for-qgc-px4-voxl2-sdk-1-3-3</link><guid isPermaLink="true">https://forum.modalai.com/topic/3818/multiagent-rtsp-stream-support-for-qgc-px4-voxl2-sdk-1-3-3</guid><dc:creator><![CDATA[ctitus]]></dc:creator><pubDate>Fri, 20 Sep 2024 17:55:06 GMT</pubDate></item><item><title><![CDATA[Mount Holes on M0153]]></title><description><![CDATA[@blue
OK thanks for the beta feedback.
We will keep that in mind. I'm sure what we did was to mimic an existing OTS product at first, and that used a backplate. I'll get with our production team to ensure we have a backplate in future kits for this version.
Thanks!
]]></description><link>https://forum.modalai.com/topic/3693/mount-holes-on-m0153</link><guid isPermaLink="true">https://forum.modalai.com/topic/3693/mount-holes-on-m0153</guid><dc:creator><![CDATA[Vinny]]></dc:creator><pubDate>Thu, 01 Aug 2024 16:37:21 GMT</pubDate></item><item><title><![CDATA[Starling 2 with ELRS 2.4GHz]]></title><description><![CDATA[@Eric-Katzfey Thank you for the clarification!
]]></description><link>https://forum.modalai.com/topic/3670/starling-2-with-elrs-2-4ghz</link><guid isPermaLink="true">https://forum.modalai.com/topic/3670/starling-2-with-elrs-2-4ghz</guid><dc:creator><![CDATA[navin_kaviyarasu]]></dc:creator><pubDate>Wed, 24 Jul 2024 05:33:41 GMT</pubDate></item><item><title><![CDATA[Update SDK docs on installing ROS2 on VOXL2]]></title><description><![CDATA[@cfirth said in Update SDK docs on installing ROS2 on VOXL2:

they

Thanks for the comment @cfirth  - this has been updated in the gitlab and is waiting to be merged for the document update!
]]></description><link>https://forum.modalai.com/topic/3359/update-sdk-docs-on-installing-ros2-on-voxl2</link><guid isPermaLink="true">https://forum.modalai.com/topic/3359/update-sdk-docs-on-installing-ros2-on-voxl2</guid><dc:creator><![CDATA[Zachary Lowell 0]]></dc:creator><pubDate>Fri, 26 Apr 2024 13:21:55 GMT</pubDate></item><item><title><![CDATA[Support for Video to Parent Computer through QGC]]></title><description><![CDATA[since voxl-streamer can provide RTSP streaming from VOXL2, ffmpeg can be used on the host machine for recording outside of QGC.
You can find some helpful information by searching ffpmeg save rtsp stream to a file . for example : https://medium.com/@tom.humph/saving-rtsp-camera-streams-with-ffmpeg-baab7e80d767
]]></description><link>https://forum.modalai.com/topic/3209/support-for-video-to-parent-computer-through-qgc</link><guid isPermaLink="true">https://forum.modalai.com/topic/3209/support-for-video-to-parent-computer-through-qgc</guid><dc:creator><![CDATA[Alex Kushleyev]]></dc:creator><pubDate>Tue, 12 Mar 2024 13:53:02 GMT</pubDate></item><item><title><![CDATA[VOXL2 Mini w&#x2F;o connectors]]></title><description><![CDATA[@tcg6000 It is possible, of course, for us to build without connectors, but it is expensive to do a custom build. There would be an MOQ of 200 units to get to similar pricing as found on our webpage.
]]></description><link>https://forum.modalai.com/topic/2870/voxl2-mini-w-o-connectors</link><guid isPermaLink="true">https://forum.modalai.com/topic/2870/voxl2-mini-w-o-connectors</guid><dc:creator><![CDATA[Moderator]]></dc:creator><pubDate>Thu, 16 Nov 2023 17:29:10 GMT</pubDate></item><item><title><![CDATA[Enabling CAN driver on VOXL2]]></title><description><![CDATA[@brinkap unfortunately, there is no CAN capability on VOXL 2. You would need to have an adapter PCB that supports CAN connects to one of the available interfaces, and then write a Linux driver that enumerates as can0
]]></description><link>https://forum.modalai.com/topic/2735/enabling-can-driver-on-voxl2</link><guid isPermaLink="true">https://forum.modalai.com/topic/2735/enabling-can-driver-on-voxl2</guid><dc:creator><![CDATA[Moderator]]></dc:creator><pubDate>Mon, 09 Oct 2023 18:55:26 GMT</pubDate></item><item><title><![CDATA[Add mask file to QVIO algorithm]]></title><description><![CDATA[@Aaky ,
Please check the following thread for more information: https://forum.modalai.com/topic/3459/masking-qvio/
My suggestion:

download the test mask from here : https://gitlab.com/voxl-public/voxl-sdk/services/voxl-qvio-server/-/blob/master/misc/mask_example_160x120.pgm . which has top half of image black (0), and bottom half white (255). values of 0 is where new features will be allowed to be detected
You can use gimp, to modify the mask and before saving you can threshold it so that the values are all 0 and 255 (nothing in between, just in case).
export from gimp as pgm (raw)
do a test with the original mask example, make sure no features are picked up in the bottom image. This is the baseline test
then try your new mask, you can also overlay the mask on top of the QVIO overlay, just like the other user did for checking.

Also please note (from the other thread) to pay attention to the fact that QVIO mask path is relative to where qvio server starts. So if you start it as a service, it's working directory will be / but if you run it manually, the working directory will be your current directory in the terminal - the other thread explains that issue.
Alex
]]></description><link>https://forum.modalai.com/topic/2551/add-mask-file-to-qvio-algorithm</link><guid isPermaLink="true">https://forum.modalai.com/topic/2551/add-mask-file-to-qvio-algorithm</guid><dc:creator><![CDATA[Alex Kushleyev]]></dc:creator><pubDate>Wed, 09 Aug 2023 16:21:39 GMT</pubDate></item><item><title><![CDATA[How to bring-up new camera module.]]></title><link>https://forum.modalai.com/topic/2345/how-to-bring-up-new-camera-module</link><guid isPermaLink="true">https://forum.modalai.com/topic/2345/how-to-bring-up-new-camera-module</guid><pubDate>Thu, 29 Jun 2023 07:21:18 GMT</pubDate></item><item><title><![CDATA[No Gps location in QGC when conent in wifi]]></title><description><![CDATA[@Samer-Jaradat What kind of a drone do you have?
]]></description><link>https://forum.modalai.com/topic/2308/no-gps-location-in-qgc-when-conent-in-wifi</link><guid isPermaLink="true">https://forum.modalai.com/topic/2308/no-gps-location-in-qgc-when-conent-in-wifi</guid><dc:creator><![CDATA[Eric Katzfey]]></dc:creator><pubDate>Thu, 22 Jun 2023 22:31:09 GMT</pubDate></item><item><title><![CDATA[Using the Drone with Motion Capture Systems]]></title><description><![CDATA[Hi Troi, thank you for the feedback. We will take this into account
]]></description><link>https://forum.modalai.com/topic/1623/using-the-drone-with-motion-capture-systems</link><guid isPermaLink="true">https://forum.modalai.com/topic/1623/using-the-drone-with-motion-capture-systems</guid><dc:creator><![CDATA[Chad Sweet]]></dc:creator><pubDate>Thu, 15 Dec 2022 16:40:22 GMT</pubDate></item><item><title><![CDATA[90 degree &amp; upside down sensor cables&#x2F;adaptors!]]></title><description><![CDATA[Thanks @Eloi for your suggestions.
We are actively working to improve our cables, cable design methods, customer communication on cables, and our image sensor flexes. It's a task we take seriously and want to improve upon.
However, it is doubtful we can use ZIF style connectors for our platforms or be able to use COTS ZIF/FFC ribbon cables. They are the least vibe/shock tolerant of any connector class which  require a lot of mechanical backing support to stay latched and engaged (and it must be movable to allow insertion and removal), thus adding weight, complexity, and size to the drone.
All of our image sensor flexes are also high-tech flex circuit assemblies, with power routing, specific ground plane control, EMI shielding, and high-speed impedance control, neither of which can be obtained from COTS FFC parts.
Hope that partly explains why we do not normally use FFC/ZIF parts.
]]></description><link>https://forum.modalai.com/topic/1622/90-degree-upside-down-sensor-cables-adaptors</link><guid isPermaLink="true">https://forum.modalai.com/topic/1622/90-degree-upside-down-sensor-cables-adaptors</guid><dc:creator><![CDATA[Vinny]]></dc:creator><pubDate>Thu, 15 Dec 2022 14:44:30 GMT</pubDate></item><item><title><![CDATA[How to integrate my ROS&#x2F;algo in VOXL2 ?]]></title><description><![CDATA[Hi Steve,
Thank you so much for these links. They will help me.
]]></description><link>https://forum.modalai.com/topic/1436/how-to-integrate-my-ros-algo-in-voxl2</link><guid isPermaLink="true">https://forum.modalai.com/topic/1436/how-to-integrate-my-ros-algo-in-voxl2</guid><dc:creator><![CDATA[mandar]]></dc:creator><pubDate>Mon, 10 Oct 2022 09:21:29 GMT</pubDate></item><item><title><![CDATA[Get PX4 not to flag GPS error when none is connected&#x2F;using VIO]]></title><description><![CDATA[@modaltb said in Get PX4 not to flag GPS error when none is connected/using VIO:

Hi @hmlow ,
Thanks for the feedback, which version of PX4 are you running?  Trying to track this down.
Thanks!

Hi
Im using ModalAI 1.11.3-0.2.3.
As a workaround i disabled the overlaid message in QGC by rebuilding a custom version of QGC.
]]></description><link>https://forum.modalai.com/topic/1416/get-px4-not-to-flag-gps-error-when-none-is-connected-using-vio</link><guid isPermaLink="true">https://forum.modalai.com/topic/1416/get-px4-not-to-flag-gps-error-when-none-is-connected-using-vio</guid><dc:creator><![CDATA[hmlow]]></dc:creator><pubDate>Sun, 02 Oct 2022 13:25:14 GMT</pubDate></item><item><title><![CDATA[VIO coordinates suddenly resets to 0,0,0 in the air!!! every flight]]></title><description><![CDATA[This is also something that we've done extensive testing with. In short, yawing can actually be one of the most reliable motions if the field of view of the camera is set up correctly. Our standard tracking sensor has a 166° diagonal/100° vertical field of view. We mount the camera at 45° down from the horizon, so the bottom of the image will be ~5° past straight down, and the corners of the frame will stretch farther into the backwards left/right swaths of area. The result of this is that yawing in place actually maintains a lot of features directly below the drone, where the bottom 10° arc will always be in view and the farther up features will stay in view for a long time. If there are a reasonable amount of features in the bottom say 20-25° below the drone it'll maintain a very robust position and yaw estimate.
However, the behavior that you're probably thinking of can also happen. We've experimented on some of our other cameras that have a wide (though not as wide as the fisheye (84° vertical)) field of view also mounted at 45° below level. The result here is that the bottom of the frame ends a couple of degrees above straight down, and so that super reliable zone of features always in view doesn't exist, and the pretty reliable zone is also much smaller. The yawing in this situation can be very unreliable, and the filter can often blow up rather quickly if not also moving during the yaw. Similarly, yawing in place with little to no features directly below you will show the same behavior, and the feature tracker will struggle to track the rapidly moving horizon-level features and can blow up.
We've also done tests with the fisheye sensor mounted straight forward which resulted in the same behavior as in the second paragraph, where the lack of downward features led to us being unable to yaw in place.
TL;DR: Yawing in place without translation as well needs to see features very close to the axis of rotation or else the filter will blow up. This can be achieved with a combination of wide fields of view and aiming the sensor not level with the horizon.
]]></description><link>https://forum.modalai.com/topic/1383/vio-coordinates-suddenly-resets-to-0-0-0-in-the-air-every-flight</link><guid isPermaLink="true">https://forum.modalai.com/topic/1383/vio-coordinates-suddenly-resets-to-0-0-0-in-the-air-every-flight</guid><dc:creator><![CDATA[[[global:former-user]]]]></dc:creator><pubDate>Tue, 27 Sep 2022 13:32:26 GMT</pubDate></item></channel></rss>