HAhagen6835·Apr 10, 2024
This one?
https://github.com/arplaboratory/learning-to-fly
That's weird, it should work
In Show HN: Universal AI Drone Controllerarplaboratory
learning-to-fly
C++2023–2024
arplaboratory / learning-to-fly
learning-to-fly
Training transferable end-to-end quadrotor control policies on a laptop in 18 seconds.
3Distinct people
5Mentions
0Explicit recommenders
594GitHub stars
What to know before exploring
What it is
Training transferable end-to-end quadrotor control policies on a laptop in 18 seconds.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week5 dated mentions
Observed mentions: 2023-12-08 22:47:41 UTC to 2024-04-10 15:23:23 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Dec 4 | 2023-12-04 00:00:00 UTC | 2023-12-11 00:00:00 UTC | 1 | 1 | 0 |
| Dec 11 | 2023-12-11 00:00:00 UTC | 2023-12-18 00:00:00 UTC | 0 | 0 | 0 |
| Dec 18 | 2023-12-18 00:00:00 UTC | 2023-12-25 00:00:00 UTC | 0 | 0 | 0 |
| Dec 25 | 2023-12-25 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 1 | 2024-01-01 00:00:00 UTC | 2024-01-08 00:00:00 UTC | 0 | 0 | 0 |
| Jan 8 | 2024-01-08 00:00:00 UTC | 2024-01-15 00:00:00 UTC | 0 | 0 | 0 |
| Jan 15 | 2024-01-15 00:00:00 UTC | 2024-01-22 00:00:00 UTC | 0 | 0 | 0 |
| Jan 22 | 2024-01-22 00:00:00 UTC | 2024-01-29 00:00:00 UTC | 0 | 0 | 0 |
| Jan 29 | 2024-01-29 00:00:00 UTC | 2024-02-05 00:00:00 UTC | 0 | 0 | 0 |
| Feb 5 | 2024-02-05 00:00:00 UTC | 2024-02-12 00:00:00 UTC | 1 | 0 | 1 |
| Feb 12 | 2024-02-12 00:00:00 UTC | 2024-02-19 00:00:00 UTC | 0 | 0 | 0 |
| Feb 19 | 2024-02-19 00:00:00 UTC | 2024-02-26 00:00:00 UTC | 0 | 0 | 0 |
| Feb 26 | 2024-02-26 00:00:00 UTC | 2024-03-04 00:00:00 UTC | 0 | 0 | 0 |
| Mar 4 | 2024-03-04 00:00:00 UTC | 2024-03-11 00:00:00 UTC | 0 | 0 | 0 |
| Mar 11 | 2024-03-11 00:00:00 UTC | 2024-03-18 00:00:00 UTC | 0 | 0 | 0 |
| Mar 18 | 2024-03-18 00:00:00 UTC | 2024-03-25 00:00:00 UTC | 0 | 0 | 0 |
| Mar 25 | 2024-03-25 00:00:00 UTC | 2024-04-01 00:00:00 UTC | 0 | 0 | 0 |
| Apr 1 | 2024-04-01 00:00:00 UTC | 2024-04-08 00:00:00 UTC | 0 | 0 | 0 |
| Apr 8 | 2024-04-08 00:00:00 UTC | 2024-04-15 00:00:00 UTC | 3 | 2 | 1 |
What Hacker News says
5 sourcesShow HN: Universal AI Drone Controller
Hey all!
I highly suggest watching the demo to visually see how much better our controller performs (2.5 min):
https://youtu.be/fWgD7tjZugY
We’ve trained ML model(s) to receive commands from a user and execute them, replacing the PID Loop(s) currently in charge of controlling most drones. We achieved this using Reinforcement Learning to train these models. Namely PPO and TD3.
These models perform better than a PID Loop, require no tuning, and retain this performance in many more situations than a PID Loop. Requiring no tuning also means that the same model is interoperable between multiple different drones/configurations, so it works out of the box!
To make these models work regardless of platform dynamics (E.g. weight, size, power, etc.), we trained it while simulating a massive amount of variation.
The models are lightweight, so most ha
Read the rest
rdware should be able to run them. However, we are still in the process of writing the wrappers for the various hardware/firmware combos. At the moment, we are working on a wrapper for hardware running PX4.
We are hoping to talk with people who want to boost the performance of their drones and remove the headaches of tuning!
If you own, fly, or work with drones and are interested in trying this out, please let us know. We are trying to learn what kinds of drones, what flight controller hardware, and what firmware people are using so we can make something that runs on your system.
If you’d like a good jumping off point to learn more, I highly suggest this repo (and the paper(s) mentioned in the repo): https://github.com/arplaboratory/learning-to-fly
Discord:
https://discord.gg/Pu7XRxJTXa
Email:
Hagenoneill@gmail.com
- SkAI
Show HN: SkAI – High performance, AI-powered, universal Drone Controller
Hey all!
We’ve trained ML model(s) to receive commands from a user and execute them, replacing the PID Loop(s) currently in charge of controlling most drones. We achieved this using Reinforcement Learning to train these models. Namely PPO and TD3.
I highly suggest watching the demo (3 min):
https://youtu.be/K4AGAfHXH38
These models perform better than a PID Loop, require no tuning, and work in many more situations than a PID Loop. Requiring no tuning also means that the same model is interoperable between multiple different drones/configurations. So it will work directly out of the box!
To make these models work regardless of platform dynamics (E.g. weight, size, power, etc.), we trained it while simulating a massive amount of variation.
The models are lightweight, so most hardware should be able to run them. However, we are still in the
Read the rest
process of writing the wrappers for the various hardware/firmware combos. At the moment, we are working on a wrapper for hardware running PX4.
We are hoping to talk with people who want to boost the performance of their drones and remove the headaches of tuning.
If you own, fly, or work with drones and are interested in trying this out, please let us know. We are trying to learn what kinds of drones, what flight controller hardware, and what firmware people are using so we can make something that runs on your system.
If you’d like a good jumping off point to learn more, I highly suggest this repo (and the paper(s) mentioned in the repo): https://github.com/arplaboratory/learning-to-fly
We are also planning on some future features (E.g. giving back some high-level tuning capabilities like prioritizing holding position vs holding orientation). Please tell us what other features you'd like to see!
Thanks!
Discord:
https://discord.gg/Pu7XRxJTXa
Email:
Hagenoneill@gmail.com
Author here. We did not pre-programm basic control or feedback parameters. The trained policy (fully connected neural network) takes the state estimate (position, orientation, linear and angular velocity) and a history of the previous actions as the input and directly outputs the PWM/RPM setpoint (uint16 that sets the pwm interval).
The code is open source, you can verify it yourself ;)
https://github.com/arplaboratory/learning-to-fly
In Tiny quadrotor learns to fly in 18 seconds