Real-Time Optimal Control via Deep Neural Networks: Study on Landing Problems
- 1 May 2018
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Guidance, Control, and Dynamics
- Vol. 41 (5), 1122-1135
- https://doi.org/10.2514/1.g002357
Abstract
Recent research has shown the benefits of deep learning, a set of machine learning techniques able to learn deep architectures, for modelling robotic perception and action. In terms of a spacecraft navigation and control system, this suggests that deep architectures may be considered now to drive all or part of the onboard decision-making system. In this paper, this claim is investigated in more detail, training deep artificial neural networks to represent the optimal control action during a pinpoint landing and assuming perfect state information. It is found possible to train deep networks for this purpose, and the resulting landings, driven by the trained networks, are close to simulated optimal ones. These results allow for the design of an onboard real-time optimal control system able to cope with large sets of possible initial states while still producing an optimal response.This publication has 16 references indexed in Scilit:
- Deep learningNature, 2015
- Deep networks for motor control functionsFrontiers in Computational Neuroscience, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Optimal control problem via neural networksNeural Computing & Applications, 2012
- Performance benchmarking of quadrotor systems using time-optimal controlAutonomous Robots, 2012
- Efficient BackPropLecture Notes in Computer Science, 2012
- Practical Recommendations for Gradient-Based Training of Deep ArchitecturesLecture Notes in Computer Science, 2012
- Convex Programming Approach to Powered Descent Guidance for Mars LandingJournal of Guidance, Control, and Dynamics, 2007
- Optimality principles in sensorimotor controlNature Neuroscience, 2004
- Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equationAutomatica, 1997