Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups
Collapse
Brand Logo

ModalAI Forum

  1. ModalAI Support Forum
  2. Ask your questions right here!
  3. Support Request Format for Best Results
  4. Mix multiple sensors for position estimation

Mix multiple sensors for position estimation

Scheduled Pinned Locked Moved Support Request Format for Best Results
6 Posts 3 Posters 1.4k Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • J Offline
    J Offline
    jocacace13
    wrote on last edited by
    #1

    Hi to all,

    I am trying to add different sensors to improve the estimation of the local position (i.e. the Local_position_ned). However, everything I made to set the ekf2 (using the px4 variables ekf2_ev params and similar) is ignored by the autopilot. I am also interested to understand more how the vision hub shares information with the px4 control stack. Is there any reference?

    Regards,

    ModeratorM 1 Reply Last reply
    0
    • J jocacace13

      Hi to all,

      I am trying to add different sensors to improve the estimation of the local position (i.e. the Local_position_ned). However, everything I made to set the ekf2 (using the px4 variables ekf2_ev params and similar) is ignored by the autopilot. I am also interested to understand more how the vision hub shares information with the px4 control stack. Is there any reference?

      Regards,

      ModeratorM Offline
      ModeratorM Offline
      Moderator
      ModalAI Team
      wrote on last edited by
      #2

      @jocacace13 Yes, the source code is available here: https://gitlab.com/voxl-public/voxl-sdk/services/voxl-vision-hub/-/blob/master/src/vio_manager.c?ref_type=heads

      A high level overview is here: https://docs.modalai.com/configure-extrinsics/

      J 1 Reply Last reply
      0
      • ModeratorM Moderator

        @jocacace13 Yes, the source code is available here: https://gitlab.com/voxl-public/voxl-sdk/services/voxl-vision-hub/-/blob/master/src/vio_manager.c?ref_type=heads

        A high level overview is here: https://docs.modalai.com/configure-extrinsics/

        J Offline
        J Offline
        jocacace13
        wrote on last edited by
        #3

        @Moderator Thanks for the quick reply. Do you think that, inspecting that source code and studying the High level architecture, I am also able to completely substitute the vision hub input, to feed the autopilot with a slam-generated odometry?

        ModeratorM 1 Reply Last reply
        0
        • J jocacace13

          @Moderator Thanks for the quick reply. Do you think that, inspecting that source code and studying the High level architecture, I am also able to completely substitute the vision hub input, to feed the autopilot with a slam-generated odometry?

          ModeratorM Offline
          ModeratorM Offline
          Moderator
          ModalAI Team
          wrote on last edited by
          #4

          @jocacace13 yes. A better approach would be to use voxl-qvio-server as a template and replace the qvio algorithm with yours.

          J 1 Reply Last reply
          0
          • ModeratorM Moderator

            @jocacace13 yes. A better approach would be to use voxl-qvio-server as a template and replace the qvio algorithm with yours.

            J Offline
            J Offline
            jocacace13
            wrote on last edited by
            #5

            Dear @Moderator, again many thanks for the reply. More or less it is clear to me the code structure. However, I am struggling with a something that I am not able to understand.

            I am connected with QGround to the voxl2 board running px4 v 1.14. I went to the mavlink inspect pane to listen to the LOCAL_POSITION_NED. Even if I stop or disable the voxl-qvio-server, the position is still received from the autopilot. How is this possible? Who is sending this data?

            Eric KatzfeyE 1 Reply Last reply
            0
            • J jocacace13

              Dear @Moderator, again many thanks for the reply. More or less it is clear to me the code structure. However, I am struggling with a something that I am not able to understand.

              I am connected with QGround to the voxl2 board running px4 v 1.14. I went to the mavlink inspect pane to listen to the LOCAL_POSITION_NED. Even if I stop or disable the voxl-qvio-server, the position is still received from the autopilot. How is this possible? Who is sending this data?

              Eric KatzfeyE Offline
              Eric KatzfeyE Offline
              Eric Katzfey
              ModalAI Team
              wrote on last edited by
              #6

              @jocacace13 PX4 sends out it's local position (as Mavlink LOCAL_POSITION_NED)

              1 Reply Last reply
              0

              Hello! It looks like you're interested in this conversation, but you don't have an account yet.

              Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.

              With your input, this post could be even better 💗

              Register Login
              Reply
              • Reply as topic
              Log in to reply
              • Oldest to Newest
              • Newest to Oldest
              • Most Votes


              ModalAI
              Categories Recent Tags ModalAI.com Docs
              © 2026 ModalAI® · Accelerating autonomy for smaller, smarter, safer drones · Powered by NodeBB
              • Login

              • Don't have an account? Register

              • Login or register to search.
              • First post
                Last post
              0
              • Categories
              • Recent
              • Tags
              • Popular
              • Users
              • Groups