Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Spacecraft proximity operation autonomous control method and system based on online learning

A technology for autonomous control and spacecraft, applied in the field of spacecraft control

Active Publication Date: 2020-08-28
BEIHANG UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the six-degree-of-freedom motion constraint problem caused by the optical load and the structure of the spacecraft body in the autonomous control task of the approaching operation of the spacecraft. The present invention provides an autonomous control method and equipment for the approaching operation of the spacecraft based on online learning. By designing the reward function related to the mission function, and using the online data to design the real-time learning law of the controller, the six-degree-of-freedom motion constraint problem in the spacecraft's near-operation mission is solved. Under the condition that the motion constraint is satisfied, the real-time learning Independently improve and optimize the performance of the controller, which improves the mission execution capability of the spacecraft control system of the control system

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
  • Spacecraft proximity operation autonomous control method and system based on online learning
  • Spacecraft proximity operation autonomous control method and system based on online learning
  • Spacecraft proximity operation autonomous control method and system based on online learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] figure 1 It is a schematic block diagram of the autonomous control system of spacecraft approaching operation based on online learning according to the present invention. The above-mentioned system is composed of a judgment network, a reward network, a learner, a controller, and a relative pose dynamic model of a spacecraft. First, the spacecraft is controlled by the initial controller, and the control performance is evaluated by the data collected by the evaluation network and the reward network. At the same time, the learner performs real-time learning of the network weights through the evaluation results, and updates the control parameters to the controller. Realize online performance improvement.

[0045] like figure 2 As shown, the steps of an autonomous control method for spacecraft approaching operations based on online learning in the present invention are as follows: firstly establish a pose dynamics model of the spacecraft approaching operation task consider...

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 spacecraft proximity operation autonomous control method and system based on online learning. In order to solve practical engineering problems of sight field constraint, proximity corridor constraint, real-time online optimization of control performance and the like of a spacecraft in a proximity operation task, the invention provides a proximity operation autonomous control technology method based on online learning. The method comprises the following steps: firstly, establishing a pose integrated kinetic model of a spacecraft based on dual quaternions, and describing pose motion constraints into an inequality form by utilizing the dual quaternions; secondly, designing a return function of online learning control based on the property of the dual quaternion fortask requirements of spacecraft approaching operation autonomous control; and finally, under a dual quaternion framework, designing an online learning method is designed to enable the controller to begradually improved from a simple control strategy to a suboptimal controller by utilizing online data. The task execution capability of the spacecraft is improved.

Description

technical field [0001] The invention relates to an autonomous control method and system for spacecraft proximity operation based on online learning, which is mainly used in tasks such as spacecraft rendezvous and docking, on-orbit supply maintenance, and coordination, and belongs to the technical field of spacecraft control. Background technique [0002] With the rapid development of aerospace technology, the diversity and complexity of spacecraft on-orbit tasks are increasing, and the mission carrier is gradually expanding from a single integrated large spacecraft system to a multi-spacecraft system. missions, derived from the emerging on-orbit missions represented by the proximity of spacecraft operations. The spacecraft proximity operation control technology is derived from important mission scenarios such as rendezvous and docking, on-orbit maintenance and replenishment. Due to factors such as flight safety, load characteristics, and mission requirements, on-orbit space...

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 Applications(China)
IPC IPC(8): G05D1/08G05D1/10G05B13/02G05B13/04
CPCG05B13/0265G05B13/042G05D1/0088G05D1/10
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 Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products