Saved in:
Bibliographic Details
Main Authors: Origer, Sebastien, Izzo, Dario, Acciarini, Giacomo, Biscani, Francesco, Mastroianni, Rita, Bannach, Max, Holt, Harry
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.03729
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909336963383296
author Origer, Sebastien
Izzo, Dario
Acciarini, Giacomo
Biscani, Francesco
Mastroianni, Rita
Bannach, Max
Holt, Harry
author_facet Origer, Sebastien
Izzo, Dario
Acciarini, Giacomo
Biscani, Francesco
Mastroianni, Rita
Bannach, Max
Holt, Harry
contents We perform uncertainty propagation on an event manifold for Guidance & Control Networks (G&CNETs), aiming to enhance the certification tools for neural networks in this field. This work utilizes three previously solved optimal control problems with varying levels of dynamics nonlinearity and event manifold complexity. The G&CNETs are trained to represent the optimal control policies of a time-optimal interplanetary transfer, a mass-optimal landing on an asteroid and energy-optimal drone racing, respectively. For each of these problems, we describe analytically the terminal conditions on an event manifold with respect to initial state uncertainties. Crucially, this expansion does not depend on time but solely on the initial conditions of the system, thereby making it possible to study the robustness of the G&CNET at any specific stage of a mission defined by the event manifold. Once this analytical expression is found, we provide confidence bounds by applying the Cauchy-Hadamard theorem and perform uncertainty propagation using moment generating functions. While Monte Carlo-based (MC) methods can yield the results we present, this work is driven by the recognition that MC simulations alone may be insufficient for future certification of neural networks in guidance and control applications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03729
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Certifying Guidance & Control Networks: Uncertainty Propagation to an Event Manifold
Origer, Sebastien
Izzo, Dario
Acciarini, Giacomo
Biscani, Francesco
Mastroianni, Rita
Bannach, Max
Holt, Harry
Systems and Control
Machine Learning
We perform uncertainty propagation on an event manifold for Guidance & Control Networks (G&CNETs), aiming to enhance the certification tools for neural networks in this field. This work utilizes three previously solved optimal control problems with varying levels of dynamics nonlinearity and event manifold complexity. The G&CNETs are trained to represent the optimal control policies of a time-optimal interplanetary transfer, a mass-optimal landing on an asteroid and energy-optimal drone racing, respectively. For each of these problems, we describe analytically the terminal conditions on an event manifold with respect to initial state uncertainties. Crucially, this expansion does not depend on time but solely on the initial conditions of the system, thereby making it possible to study the robustness of the G&CNET at any specific stage of a mission defined by the event manifold. Once this analytical expression is found, we provide confidence bounds by applying the Cauchy-Hadamard theorem and perform uncertainty propagation using moment generating functions. While Monte Carlo-based (MC) methods can yield the results we present, this work is driven by the recognition that MC simulations alone may be insufficient for future certification of neural networks in guidance and control applications.
title Certifying Guidance & Control Networks: Uncertainty Propagation to an Event Manifold
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2410.03729