Compatible Stereo Camera and live streaming components - NON GPS

[nitinpatil]

Hello Team,
We are new to use VOXL2 componets. We are looking to use VOXL2 for building our non-gps agriculture drones.
Can you please suggest the components which can be used for building the non-gps application for SLAM based navigation

1. Stereo camera - of ModalAI for non-gps application using SLAM based navigation
2. Camera for live streaming
3. Does the VOXL2 support both Ardupilot and PX4? We are ok to use PX4 as well but will prefer ardupilot. Which is strongly recommended?

Please suggest the components for building above given application so that we can place the order.

Thanks & Regards

[Eric Katzfey]

@nitinpatil Regarding question #3, both ArduPilot and PX4 are supported. Since most of our customers are currently using PX4 we have much more experience with that.

[nitinpatil]

@Eric-Katzfey Many thanks for your reply. Then we will also prefer PX4.
Kindly see if we can get answers for below two questions as well.

Which Modal AI components can be used for developing non-gps applications, mainly the supporting libraries/code should be available for suggested devices.

1. Which Stereo camera or Sensor - of ModalAI for non-gps application using SLAM based navigation
2. Which Camera for live streaming on ground control station

Thanks & Regards

[nitinpatil]

This post is deleted!

[nitinpatil]

Dear members,

Can anyone please reply to below questions.

As per the product catalog, I have shortlisted below components, please confirm if these 3 components are enough for developing non-gps drones which will be using slam based navigation in indoor / confined space applications.

1. VOXL2 autopilot -- https://www.modalai.com/products/voxl-2?variant=39914779836467
2. VOXL 2 Time of Flight (TOF) Depth Sensor -- https://www.modalai.com/collections/image-sensors/products/m0178?variant=48528287793456
3. VOXL 2 Mini 40-Pin Connector TOF Adapter (MDK-M0172-1-00). -- https://www.modalai.com/products/mdk-m0172-1-00

Please confirm if these components are enough to develop non-gps applications in confined spaces using PX4 or am I missing any component?

[Moderator]

@nitinpatil Hi Nitin, we don't know what algorithm you are trying to develop. You'll have to choose sensors based on what algorithm you are trying to develop.

[nitinpatil]

@Moderator Many thanks for your reply

Our goal is to develop a drone capable of indoor/confined-space autonomous flight without GPS, using SLAM-based navigation. The system should perform 3D mapping, obstacle avoidance, and full-area path planning.

We would like to confirm the correct set of components and the required algorithm stack.

Planned Algorithm Stack:

1. State Estimation: QVIO (Visual-Inertial Odometry) providing position and velocity to PX4/EKF2 via voxl-vision-hub.
2. Mapping: voxl-mapper (TSDF/ESDF) using a depth source.
3. Planning and Avoidance: voxl-mapper’s path planner or PX4 avoidance, using VIO as the pose source.
4. Autopilot: PX4 running on VOXL2 via voxl-px4.

Proposed Hardware:

1. VOXL2 Autopilot – https://www.modalai.com/products/voxl-2?variant=39914779836467
2. VOXL2 Tracking Camera (Mono Global-Shutter) – required for QVIO (please confirm the correct part number). -- https://www.modalai.com/collections/image-sensors/products/msu-m0149-1
3. VOXL2 Compatible adapter https://www.modalai.com/products/mdk-m0076-1
4. VOXL2 Time-of-Flight (ToF) Depth Sensor – https://www.modalai.com/products/m0178?variant=48528287793456
5. VOXL2 Mini 40-Pin Connector ToF Adapter (MDK-M0172-1-00) – https://www.modalai.com/products/mdk-m0172-1-00

Questions:

1. Please confirm if this set (VOXL2 + Tracking Camera + Camera adapter + ToF sensor + ToF adapter) is sufficient for robust indoor SLAM navigation using PX4.
2. For the tracking camera, which exact ModalAI part number is recommended for QVIO on VOXL2?
3. Are there any best-practice configurations for voxl-mapper when using ToF instead of stereo depth?
4. Would you recommend any additional sensors for improved performance in larger or more complex indoor environments?

Goal Summary:
We want the drone to hold position, generate a 3D occupancy map, avoid obstacles, and autonomously plan paths throughout the flyable space—without any GPS input.

Thank you in advance for your guidance and confirmation.

Best regards,
Nitin