Reinforcement learning nonlinear attitude control method for quadrotor UAV

A four-rotor unmanned aerial vehicle, reinforcement learning technology, applied in attitude control, non-electric variable control, vehicle position/route/height control, etc., can solve the problem of insufficient generalization ability of the controller, achieve precise control, improve The effect of robustness

Active Publication Date: 2021-12-07
TIANJIN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention considers the unmodeled part in the dynamics model of the quadrotor UAV, and uses the reinforcement learning method and the multivariable super-twisting algorithm to carry out online training for the quadrotor UAV to solve the problem of insufficient generalization ability of the controller

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Reinforcement learning nonlinear attitude control method for quadrotor UAV
  • Reinforcement learning nonlinear attitude control method for quadrotor UAV
  • Reinforcement learning nonlinear attitude control method for quadrotor UAV

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] The technical scheme adopted by the present invention is: establish a kind of quadrotor unmanned aerial vehicle dynamics model including the unmodeled part of the system, and design the corresponding reinforcement learning nonlinear attitude controller, including the following steps:

[0085] First, a dynamic model of the quadrotor UAV needs to be established. figure 1 It is a schematic diagram of the quadrotor UAV system used in this paper. In the present invention, the unmanned aerial vehicle is an X-shaped four-rotor unmanned aerial vehicle, and adopts the Newton-Euler method to establish the dynamic model of the four-rotor unmanned aerial vehicle, and the expression is as follows:

[0086]

[0087] The variables in formula (1) are defined as follows: M(η) represents the inertia matrix, represents the Coriolis and centrifugal force matrices, Represents the rotational damping coefficient matrix, where K 1 、K 2 and K 3 are all unknown constants. Δ(η) repre...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a non-linear attitude control method for quadrotor UAV reinforcement learning. Aiming at the quadrotor UAV attitude control problem with unmodeled parts in the dynamic model of the quadrotor UAV, the reinforcement based on the execution-evaluation neural network is designed. The learning controller is used to estimate the unmodeled part of the model, and at the same time, a nonlinear robust controller based on multivariable super-twisting is designed to realize the attitude stability control of the quadrotor UAV.

Description

technical field [0001] The invention relates to the precise attitude control of a quadrotor UAV. Aiming at the influence of the unmodeled part of the quadrotor UAV system dynamics model on the system control performance, and the dependence of the control method based on the system dynamics model on the accurate model, a control algorithm based on reinforcement learning and second-order sliding mode is proposed The nonlinear attitude controller of the UAV achieves the result of finite time convergence of the UAV attitude control error. Specifically, it relates to a finite-time convergent attitude control method for a quadrotor UAV. Background technique [0002] Traditional linear control algorithms, such as PID algorithm and LQR algorithm, have been widely used in quadrotor UAVs. However, the linear control algorithm only ensures that the system has a good control effect in the state near the equilibrium point, and it is difficult to achieve satisfactory results in dealing ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G05D1/08
CPCG05D1/0825
Inventor 鲜斌张诗婧
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap