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

Gaussian process trajectory tracking control method for space robot

A space robot and Gaussian process technology, applied in the direction of program control manipulators, manipulators, manufacturing tools, etc., can solve problems such as lack of integration, limited accuracy of dynamic models, and inability to measure model confidence

Active Publication Date: 2021-02-05
SOUTHEAST UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these technologies are limited to algorithm improvements and lack of integration with practical applications.
[0006] Among the existing space robot trajectory tracking control methods, the model-based methods are limited by the accuracy of the dynamic model, and the data-based methods are mostly faced with the problem of not being able to measure the confidence of the model
At present, there is no trajectory tracking control method that can better apply non-parametric Bayesian machine learning methods such as Gaussian process models.

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
  • Gaussian process trajectory tracking control method for space robot
  • Gaussian process trajectory tracking control method for space robot
  • Gaussian process trajectory tracking control method for space robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Embodiment 1: see figure 2 , a space robot Gaussian process trajectory tracking control method, the method comprises the following steps:

[0079] Step (1) Based on the sparse Gaussian process model, the dynamic model of the space robot system is identified;

[0080] Step (2) Combining the identified system with the computational torque control method to obtain a Gaussian process control law;

[0081] Step (3) In the control process, the system model is updated online based on the edge particle filter method according to the data obtained in real time.

[0082] Further, the step (1) includes:

[0083] (11) Establish a dynamic model and set the input and output of the Gaussian process model

[0084] The dynamic model of the space robot is

[0085]

[0086] in is the generalized variable of the robot system, u(t) is the control input. f(p) is the unknown dynamic influence that cannot be accurately modeled, M(q) is the generalized inertia matrix, is the gene...

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 a Gaussian process trajectory tracking control method for a space robot for carrying out online identification on a kinetic model of a space robot system and dynamically adjusting and controlling a gain by utilizing the confidence coefficient of the model. Furthermore, a sparsification method based on guide data points is adopted for online training of the Gaussian processkinetic model, and meanwhile, an edge particle filter is adopted for online estimation of hyper-parameters of the Gaussian process model, so that the computational burden of model training and prediction is effectively reduced.

Description

technical field [0001] The invention relates to the technical field of trajectory tracking control, in particular to a Gaussian process trajectory tracking control method for a space robot. Background technique [0002] In the space exploration program, the application of space robots can help humans complete very dangerous and difficult tasks. In space station orbit assembly, maintenance and repair tasks, space robots play a very important role. Trajectory tracking control of space robot is an important technology in the application of space robot. With the continuous development of system identification theory and control theory, control methods based on data and machine learning are continuously proposed, which greatly improves the trajectory tracking control performance when the system model is unknown. [0003] "Adaptive Neural Robust Control for Model-Unknown Free-floating Space Manipulators", published in "Journal of China Engineering Machinery" (Wang Chao, Jiang Li...

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): B25J9/16
CPCB25J9/1664B25J9/1612B25J9/163
Inventor 符启恩孙长银陆科林
Owner SOUTHEAST 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