A Reinforcement Learning Attitude Constraint Control Method Considering Actuator Installation Deviation

A technology of actuators and installation deviations, applied in attitude control, space navigation equipment, space navigation aircraft, etc., to achieve the effect of improving execution efficiency, improving control performance, improving economy and mission execution.

Active Publication Date: 2022-05-20
BEIHANG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a method of reinforcement learning attitude constraint control that considers the installation deviation of the actuator to solve the problem that the spacecraft has attitude motion constraints due to the load limitation and the actuator has deviations during the installation process. attitude control problem

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
  • A Reinforcement Learning Attitude Constraint Control Method Considering Actuator Installation Deviation
  • A Reinforcement Learning Attitude Constraint Control Method Considering Actuator Installation Deviation
  • A Reinforcement Learning Attitude Constraint Control Method Considering Actuator Installation Deviation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Step 1: According to the dynamic characteristics of the spacecraft on-orbit attitude maneuver mission, based on the modified Rodrigues parameters, establish the dynamic model of the spacecraft on-orbit attitude maneuver mission considering the installation deviation of the actuator and the interference model, and Algebraically characterize the attitude kinematics constraints in the on-orbit attitude maneuvering mission.

[0067] Based on the modified Rodrigues parameters, the dynamic model of the spacecraft on-orbit attitude maneuver mission is established as follows:

[0068]

[0069] Define H(σ bt )for:

[0070]

[0071] in, Indicates the relative attitude of the controlled spacecraft to the desired attitude, Indicates the relative angular velocity between the controlled spacecraft and the desired attitude in the spacecraft body coordinate system, σ bt and The initial value of can be selected as [-0.4622,0.4074,0.5100] T and [0,0,0] T ;J b Indicates t...

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 discloses an attitude constraint control method of reinforcement learning considering the installation deviation of the actuator. First, based on the modified Rodrigues parameters, a dynamic model of the spacecraft is established considering the installation deviation of the actuator and the interference model, and the attitude movement Then, the reward function is designed according to the requirements of the on-orbit attitude maneuver task; finally, the corresponding additional cost item is proposed for the installation deviation and interference, and the spacecraft attitude control based on reinforcement learning is designed by combining the dynamic model and the reward function. method; in this way, by designing the reward function related to the mission function, designing the corresponding additional cost item for the installation deviation and interference, using the online data to design the real-time parameter learning law of the controller, and solving the motion of the spacecraft under the condition of installation deviation and interference Constraint problems, the controller is gradually upgraded from a simple control strategy to a suboptimal controller, so as to improve the execution effectiveness of spacecraft on-orbit tasks.

Description

technical field [0001] The invention is mainly applied to spacecraft on-orbit service, astronomical redirection observation, attitude rapid maneuvering, etc., belongs to the technical field of spacecraft control, and in particular relates to an attitude constraint control method of reinforcement learning considering the installation deviation of actuators. Background technique [0002] With the rapid development of aerospace technology, space missions are gradually developing in the direction of deep space and long-distance diversity, and the scientific payloads carried by spacecraft are becoming more and more diverse and complex. On the one hand, most of these scientific instruments are mainly optical instruments, which need to point to avoid the direction of strong light during on-orbit maneuvering, so as to protect the optical sensitive components of scientific instruments, which requires consideration of the motion trajectory when designing the control system Safety cons...

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): G05D1/08B64G1/24
CPCB64G1/244B64G1/245Y02T90/00
Inventor 胡庆雷杨昊旸郑建英郭雷
Owner BEIHANG 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