Artificial Intelligence
Mission Analysis
1 Jan 2017

G&C Networks - Deep architectures for real time optimal actions

Recent research on deep learning, a set of machine learning techniques able to learn deep architectures, has shown how robotic perception and action greatly benefits from these techniques. In terms of spacecraft navigation and control system, this suggests that deep architectures may be considered now to drive all or part of the on-board decision making system. In this project we prove that it is possible to train deep artificial neural networks to represent the optimal control action during different scenarios.

The resulting networks, called G&CNETS or gecnets, are able to safely perform the required task when trained accurately.

Our results allow for the design and validation of an on-board real time optimal control system able to cope with large sets of possible initial states while still producing an optimal response.

In the video above we show the logic of our research and we show, at the very end, an optimal landing of a Falcon 9 rocket completely driven by a G&CNET that takes its inputs from a second convolutional neural network trained to reconstruct the state (pose estimation) of the rocket.

In collaboration with TU Delft, we have extended the work on G&CNETs to on-board real-time optimal control of quadcopters which you can read more about here.

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
Mission Analysis Conference paper
Aggressive Online Control of a Quadrotor via Deep Network Representations of Optimality Principles
S. Li and E. Öztürk and C. De Wagter and G. C. H. E. de Croon and D. Izzo
2020 IEEE International Conference on Robotics and Automation (ICRA): 6282-6287
(2020)
Download
BibTex
Mission Analysis Conference paper
Learning Dynamic-Objective Policies from a Class of Optimal Trajectories
C. I. Sprague and D. Izzo and P. Ögren
2020 59th IEEE Conference on Decision and Control (CDC): 597-602
(2020)
Download
BibTex
Hamburger icon
Menu
Advanced Concepts Team