Artificial Intelligence
Mission Analysis
Jun 1, 2018

G&CNets - On-Board Optimal Control of a Quadcopter

In collaboration with TU Delft, we have further investigated the use of G&CNets for real-time optimal control by training and testing these networks onboard the Parrot Bebop drone in the TU Delft MAVLab.

By training a deep neural network on the optimal controls for time optimal flight, we were able to outperform one of the more commonly used, state-of-the-art controllers based on minimising the snap (4th time derivative of position). Below are videos showing the flight path and timing of the two controllers starting from the same position.

Benchmark controller:

G&CNet Controller:

These videos show that the G&CNet controller follows a similar control pattern, but significantly more aggressive for faster flight. All of the control computation is done on-board based on the state of the quadcopter thus showing that it is possible to run a neural network on-board and achieve optimal flight.

A publication has been submitted to IEEE Robotics and Automation Letters and is awaiting review. Here you can find our previous work on G&CNets, and here the application of G&CNets to interplanetary trajectories. This page will be updated when the paper is published so stay tuned!

Outcome

Artificial Intelligence Conference paper
Learning the optimal state-feedback using deep networks
Sanchez-Sanchez, C. and Izzo, D. and Hennes, D.
2016 IEEE Symposium Series on Computational Intelligence (SSCI)
(2016)
Download
BibTex
Artificial Intelligence Conference paper
Optimal Real-Time Landing Using Deep Networks
Sanchez-Sanchez, C. and Izzo, D. and Hennes, D.
6th International Conference on Astrodynamics Tools and Techniques (ICATT)
(2016)
Download
BibTex
Artificial Intelligence Peer reviewed article
Real-Time Optimal Control via Deep Neural Networks: Study on Landing Problems
Sanchez-Sanchez, C. and Izzo, D.
Journal of Guidance Control and Dynamics 41, no. 5: 1122-1135
(2018)
Download
BibTex
Hamburger icon
Advanced Concepts Team