Scholarlink

Abstract <p>We consider the problem of aircraft motion control in uncertain conditions caused by incomplete and inaccurate knowledge of the aircraft characteristics, as well as by abnormal situations in flight, which affect the properties of the aircraft as the control object. One of the effective tools for solving problems of this kind, providing the adjustment of aircraft control algorithms taking into account its changed dynamics, is reinforcement learning (RL) in the approximate dynamic programming (ADP) variant in combination with artificial neural networks. In the past decade, a family of methods known as adaptive critic design (ACD) has been actively developed within the ADP approach to control the behavior of complex dynamic systems. This paper discusses the application of one variant of the ACD approach, namely, single network adaptive critic (SNAC) and its development through combined use with the dynamic inversion (DI) method. This approach makes it possible to form an optimal adaptive control law for the motion of an aircraft. Its effectiveness is demonstrated on the example of longitudinal motion control for a supersonic transport (SST) airplane.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Combined Use of Dynamic Inversion and Reinforcement Learning for Optimal Adaptive Control of Supersonic Transport Airplane Motion

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • G. Dhiman,
  • Yu. V. Tiumentsev,
  • R. A. Tskhay

摘要

Abstract

We consider the problem of aircraft motion control in uncertain conditions caused by incomplete and inaccurate knowledge of the aircraft characteristics, as well as by abnormal situations in flight, which affect the properties of the aircraft as the control object. One of the effective tools for solving problems of this kind, providing the adjustment of aircraft control algorithms taking into account its changed dynamics, is reinforcement learning (RL) in the approximate dynamic programming (ADP) variant in combination with artificial neural networks. In the past decade, a family of methods known as adaptive critic design (ACD) has been actively developed within the ADP approach to control the behavior of complex dynamic systems. This paper discusses the application of one variant of the ACD approach, namely, single network adaptive critic (SNAC) and its development through combined use with the dynamic inversion (DI) method. This approach makes it possible to form an optimal adaptive control law for the motion of an aircraft. Its effectiveness is demonstrated on the example of longitudinal motion control for a supersonic transport (SST) airplane.