A Domain-Knowledge-Aided Deep Reinforcement Learning Approach for Flight Control Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shin, Hyo-Sang, He, Shaoming, Tsourdos, Antonios
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913566286675968
author Shin, Hyo-Sang
He, Shaoming
Tsourdos, Antonios
author_facet Shin, Hyo-Sang
He, Shaoming
Tsourdos, Antonios
contents This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning efficiency and generalisability. More specifically, the proposed approach fixes the autopilot structure as typical three-loop autopilot and deep reinforcement learning is utilised to learn the autopilot gains. To solve the flight control problem, we then formulate a Markovian decision process with a proper reward function that enable the application of reinforcement learning theory. Another type of domain knowledge is exploited for defining the reward function, by shaping reference inputs in consideration of important control objectives and using the shaped reference inputs in the reward function. The state-of-the-art deep deterministic policy gradient algorithm is utilised to learn an action policy that maps the observed states to the autopilot gains. Extensive empirical numerical simulations are performed to validate the proposed computational control algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_1908_06884
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle A Domain-Knowledge-Aided Deep Reinforcement Learning Approach for Flight Control Design
Shin, Hyo-Sang
He, Shaoming
Tsourdos, Antonios
Artificial Intelligence
Machine Learning
Systems and Control
This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning efficiency and generalisability. More specifically, the proposed approach fixes the autopilot structure as typical three-loop autopilot and deep reinforcement learning is utilised to learn the autopilot gains. To solve the flight control problem, we then formulate a Markovian decision process with a proper reward function that enable the application of reinforcement learning theory. Another type of domain knowledge is exploited for defining the reward function, by shaping reference inputs in consideration of important control objectives and using the shaped reference inputs in the reward function. The state-of-the-art deep deterministic policy gradient algorithm is utilised to learn an action policy that maps the observed states to the autopilot gains. Extensive empirical numerical simulations are performed to validate the proposed computational control algorithm.
title A Domain-Knowledge-Aided Deep Reinforcement Learning Approach for Flight Control Design
topic Artificial Intelligence
Machine Learning
Systems and Control
url https://arxiv.org/abs/1908.06884