Hi, we’re Antilatency, and we’ve developed a tracking system. We started working on it in 2016, released it in 2019, and we’re proud to say that now over 1500 VR and Virtual Production customers in 60+ countries have their projects powered by Antilatency tracking. Recently we started working on an autonomous drone landing system, and we’re excited to show you our MVP. We call it CoPilot.

We used our positional tracker with Raspberry Pi connected to PX4 autopilot (pixhawk) via MAVLink protocol. Since our tracker together with Raspberry Pi weighs only 80 grams and requires 4.25 watts, it makes it perfect for this use case.

The tracker gets its position relative to an infrared layout on a landing pad, made with active IR markers. Markers make up a pattern complex enough for a tracker to not confuse it with other light sources and random reflections on the ground. Varying marker patterns also let the tracker recognize a specific landing pad out of multiple pads in the area.

copter1.jpg

Infrared markers are just a source of infrared light (850 nm) without any modulation or control from the drone. There are no radio receivers and antennas at the landing area, which makes the system not only robust and easy to set up, but also unaffected by radio interference.

The tracking system processes all the image data onboard, without recording or transmitting a real picture of the environment, which eliminates privacyissues. It’s a necessary feature for delivery drones.

In this demo, the drone is able to execute autonomous landing within 5 meters from the landing pad, and this distance grows with the power of markers.

So this is what we’ve been working on so far, and we’ve put our project up on GitHub. This is the CoPilot MVP code for Raspberry Pi. The app asks PX4 for FlightMode, and once the mode changes to ‘land’, it activates off-board mode and takes over to land the drone with precision. ‘FlightMode‘ changes to ‘land‘ after you send a corresponding command with ‘QGroundControl‘ during the flight, or from your RC with this command assigned to one of the switches. Go ahead and check out the CoPilot repository, dig deeper, and get involved.

We would love for developers to join us in driving this project further, and see you tune it to match your needs and expectations, so please join our Discord server where we will be sharing our progress going forward, answering your questions, and trying out new things together.

We’re also launching a developers program, and you can participate by telling us all about your drone projects, and how CoPilot may complement your work. We want to set the best projects up with our Dev Kits.
copter_setup.jpg
The kit includes: a 10 sqm tracking area, an Alt tracker, and a USB socket. Go ahead and check out #developers-program channel on CoPilot Discord for further instructions on how to get into our dev program.

We would appreciate it if you shared this post (or CoPilot website) with fellow developers that might be interested in getting their hands dirty with the project. We believe that precise auto drone landing will unlock new opportunities in multiple industries, and we welcome everyone who wants to tag along for the ride.

You need to be a member of diydrones to add comments!

Join diydrones

Replies

  • Hi everyone, we're excited to share the results we got after testing Copilot - our precise drone landing system - outdoors.

    https://youtu.be/LEae31UI9jY

    We assembled an environment with 5W IR markers, and painted it black for anti-glare protection. The Alt tracker recognizes the 12-marker pattern on the landing pad even under direct sunlight. It allows the drone to execute precise landing autonomously even when influenced by elements.

    We keep you updated on how this project is coming along on our Discord server, where you can also take part in the Copilot Dev program. Tell us about your drone projects, and how you would implement Copilot into your solution, and we'd be happy to set you up with a kit: https://discord.gg/c2EKzc2kWH
This reply was deleted.

Activity

DIY Robocars via Twitter
RT @a1k0n: Did I get rid of hand-tuned parameters? Yes. Am I still hand-tuning more parameters? Also yes. I have a few knobs to address the…
yesterday
DIY Robocars via Twitter
RT @a1k0n: I'm not going to spoil it, but (after charging the battery) this works way better than it has any right to. The car is now faste…
yesterday
DIY Robocars via Twitter
RT @a1k0n: Decided to just see what happens if I run the sim-trained neural net on the car, with some safety rails around max throttle slew…
yesterday
DIY Robocars via Twitter
Saturday
DIY Robocars via Twitter
RT @SmallpixelCar: @a1k0n @diyrobocars I learned from this. This is my speed profile. Looks like I am too conservative on the right side of…
Saturday
DIY Robocars via Twitter
RT @a1k0n: @SmallpixelCar @diyrobocars Dot color is speed; brighter is faster. Yeah, it has less room to explore in the tighter part, and t…
Saturday
DIY Robocars via Twitter
RT @a1k0n: I'm gonna try to do proper offline reinforcement learning for @diyrobocars and throw away all my manual parameter tuning for the…
Friday
DIY Robocars via Twitter
RT @circuitlaunch: DIY Robocars & Brazilian BBQ - Sat 10/1. Our track combines hairpin curves with an intersection for max danger. Take tha…
Thursday
DIY Robocars via Twitter
RT @SmallpixelCar: Had an great test today on @RAMS_RC_Club track. However the car starts to drift at 40mph. Some experts recommended to ch…
Sep 11
DIY Robocars via Twitter
RT @gclue_akira: 世界最速 チームtamiyaのaiカー https://t.co/1Qq2zOeftG
Sep 10
DIY Robocars via Twitter
RT @DanielChiaJH: Always a good time working on my @diyrobocars car at @circuitlaunch. Still got some work to do if I’m to beat @a1k0n howe…
Sep 10
DIY Robocars via Twitter
RT @SmallpixelCar: My new speed profile for @RAMS_RC_Club track https://t.co/RtLb7TcgIJ
Sep 10
DIY Robocars via Twitter
RT @SmallpixelCar: Practiced at @RAMS_RC_Club today with my new @ARRMARC car https://t.co/AEu2hCx89T
Aug 28
DIY Robocars via Twitter
Aug 24
DIY Robocars via Twitter
RT @gclue_akira: 柏の葉で走行させてるjetracerの中身 #instantNeRF #jetracer https://t.co/giVvuE4hP7
Jul 4
DIY Robocars via Twitter
Cool web-based self-driving simulator. Click save when the AI does the right thing https://github.com/pncsoares/self-driving-car
Jul 4
More…