Starling 2 Max for indoor
-
Hello,
We are looking for an indoor drone to learn on and develop some of our own solutions on. We really like your open Starling 2 platform. We would just like to ask about the sensors and capabilities of the Starling 2 Max platform. We have large spaces and this larger platform that can carry some additional load would be more suitable for us. But is it also suitable for indoor mapping, autonomous navigation, etc.? Or is it possible to modify it somehow to make it work? I'm asking because it is not explicitly written for the Starling 2 Max, but it is for the Starling 2.
Thanks!
-
@Jakub-Tvrz The sensor stack on Starling 2 Max should be the same as Starling 2
-
@tom said in Starling 2 Max for indoor:
The sensor stack on Starling 2 Max should be the same as Starling 2
However, I read on the website that the Starling 2 explicitly includes obstacle avoidance, etc., and the sensor equipment also seems to be a bit different, so I'm wondering if the Starling 2 Max is also suitable for indoor flights with warehouse inventory tests, etc.
Starling 2:
● Triple AR0144 1MP fisheye CV image sensor for visual inertial odometry (VIO)
● Single IMX412 12MP color image sensor for streaming, recording and snapshots
● Next Generation PMD ToF image sensor for obstacle avoidance and 3D mapping● Multi-Cam Visual Inertial Odometry (VIO) to navigate in GPS denied environments
● Visual Obstacle Avoidance (VOA) to fly safely in tight spaces
● 3D Mapping and Path Planning to fly hands-off in dynamic environments
● Support for open-source ecosystems: OpenCV, ROS 2, Docker, MAVROS, MAVSDK
● Integrated PX4 and Ardupilot flight controllers accelerated by onboard DSPStarling 2 Max:
● Dual AR0144 1MP fisheye CV cameras for Visual Inertial Odometry
● Dual IMX412 12MP cameras (forward and down) for image streaming & capture
● Single FLIR Lepton for thermal image and video capture● Visual Inertial Odometry to navigate in GPS denied environments
● Multiple image sensors fused for VIO in dynamic environments
● TensorFlow-Lite Neural Networks run object classification, detection & other
models
● Open-source software: OpenCV, ROS 2, Docker, upstream PX4 -
@Jakub-Tvrz said in Starling 2 Max for indoor:
● Next Generation PMD ToF image sensor for obstacle avoidance and 3D mapping
@Jakub-Tvrz if you purchased the starling 2 Max version that comes with the PMD TOF then you will be capable of running PX4's instance of visual obstacle avoidance - however, it is not... great.
● Next Generation PMD ToF image sensor for obstacle avoidance and 3D mapping
https://www.modalai.com/collections/all/products/starling-2-max?variant=49129974169904 <-- this the version you will had to buy for the TOF sensor
