There’s a great deal of research happening around the topic of autonomous vehicles of all creeds and colours. [Ryan] decided this was an interesting field, and took on an autonomous drone as his final project at Cornell University.
The main idea was to create a drone that could autonomously follow a target which provided GPS data for the drone to follow. [Ryan] planned to implement this by having a smartphone provide GPS coordinates to the drone over WiFi, allowing the drone to track the user.
As this was a university project, he had to take a very carefully considered approach to the build. Given likely constraints on both money and time, he identified that the crux of the project was to develop the autonomous part of the drone, not the drone itself. Thus, off-the-shelf parts were selected to swiftly put together a drone platform that would serve as a test bed for his autonomous brain.
The write up is in-depth and shares all the gritty details of getting the various subsystems of the drone talking together. He also shares issues that were faced with altitude control – without any sensors to determine altitude, it wasn’t possible to keep the drone at a level height. This unfortunately complicated things and meant that he didn’t get to complete the drone’s following algorithm. Such roadblocks are highly common in time-limited university projects, though their educational value cannot be overstated. Overall, while the project may not have met its final goals, it was obviously an excellent learning experience, and one which has taught him plenty about working with drones and the related electronics.
For another take on autonomous flight, check out this high-speed AI racing drone.
These project confuse me. These problems were solved years ago in the open source community with project such as APM and PX4 and today there are toy drones that you can buy on the shelves of Wal-mart do all of this, to say nothing of countless cheap autopilots you can buy on Amazon. What is the point of doing it again from scratch, badly? Why not focus on problems that haven’t be solved countless times before?
Learning experience. New take on old ideas. Trying to do things better.
And if you actually played with the APM/Pixhawk codebases, and their “APIs”….well, youd know that we need new, leaner solutions.
“Learning experience. New take on old ideas.”
Yes but tracking a cell phone would be a stepp backwards compared of the shelf parts.
Wich we also saw as the result a non rtk gps for altitude hold wont work. This project was more into achiving stable fligth. If he wanted to expriment with autonomous fligth it would have been better to start with a fligth computer that already can fly the drone and connect that to a smarter unit with sterovision tracking etc.
But still il bet that he learnd alot and had a fun excperince, in the end that is what matters.
Why do we bother teaching children how to build out of LEGO? It’s all been done years ago!
It’s about the learning experience. If you don’t do, you don’t learn.
Yes, someone else has made a drone before. Ryan wanted to learn how to do it himself.
Excellent example
I doubt many of us are capable of building truly new and never-seen-before technology. Have you? Sometimes reinventing the wheel is good for the sake of learning, or pride, or just for the hell of it. Most of us are hobbyists.
Tee-hee. Got it.
I love this project. I had a kind of loose idea a while ago to design some kind of autonodrone that would find a nice, high, sheltered place to land and recharge with solar cells during the day, then wander around at night collecting data of some kind. Before its batteries ran down too much it would find another safe, hidden spot and standby until morning.
I didn’t quite figure out a good purpose for it, but I think it would be an interesting challenge.
http://www.radiolab.org/story/update-eye-sky/