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

Collaborative path tracking control method for limited mobile robots based on neural network

A mobile robot and neural network technology, applied in the field of cooperative path tracking control of limited mobile robots, can solve unknown parameters or nonlinear modeling uncertainties, cannot deal with nonlinear modeling uncertain items, and increase the difficulty of mobile robot controllers And other issues

Active Publication Date: 2020-01-07
SOUTH CHINA UNIV OF TECH +1
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In addition, mobile robots usually have problems such as unknown parameters or nonlinear modeling uncertainties. The existence of these problems increases the difficulty of mobile robot controller design. How to effectively identify unknown parameters or nonlinear modeling uncertainties is the field of intelligent control. one of the difficult subjects
Currently, adaptive control methods provide an efficient way to deal with unknown parameters, however, this method cannot deal with nonlinear modeling uncertainties

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
  • Collaborative path tracking control method for limited mobile robots based on neural network
  • Collaborative path tracking control method for limited mobile robots based on neural network
  • Collaborative path tracking control method for limited mobile robots based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0112] Such as figure 1 As shown, the present embodiment provides a neural network-based cooperative path tracking control method for limited mobile robots, including the following steps:

[0113] Step 1, such as figure 2 As shown, the kinematics and dynamics model of a single mobile robot is established, and then the model equation is converted, the basic kinematics and dynamics model is converted into a differential equation of pose and state, and extended to the i-th mobile robot, In this embodiment, three mobile robots are used for illustration in the formation;

[0114] The kinematics and dynamics model of a single mobile robot is established as:

[0115]

[0116]

[0117] where, η = [x, y, ψ] T , x, y, ψ are the position (x, y) and direction angle (ψ) of the mobile robot respectively, w=[w 1 ,w 2 ] T ,w 1 ,w 2 are the angular velocities of the left and right wheels of the mobile robot, τ=[τ 1 , τ 2 ], τ 1 , τ 2 are the control torques of the left and r...

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 collaborative path tracking control method for limited mobile robots based on a neural network. The collaborative path tracking control method comprises the steps that a kinematic and dynamic model of each mobile robot is established; a path tracking error equation is defined; a performance-limited tan-type obstacle Lyapunov function of the mobile robots is established; the formation mode of the multiple mobile robots is established based on graph theory knowledge; a path parameter update rate equation of each mobile robot is established; aiming at nonlinear modelinguncertain items of the mobile robots, a controller based on the neural network is designed through a backstepping design method; and a formation controller is designed. It can be not only ensured thatthe path tracking error of each single mobile robot is eventually converged to a small neighborhood, but also ensured that the errors are always within a given interval, transient performance is ensured, and meanwhile, the multiple mobile robots are collaboratively controlled, so that the multiple mobile robots are evenly distributed on the same path according to path parameters.

Description

technical field [0001] The invention relates to the field of mobile robot formation control, in particular to a neural network-based cooperative path tracking control method for limited mobile robots. Background technique [0002] At present, mobile robots have many applications in practical scenarios, such as unmanned delivery vehicles, automatic sorting of express delivery, automatic transportation of goods in ports, and even unmanned driving technology. With the continuous expansion of robot application fields, people have higher and higher requirements on the control performance of mobile robots, including transient performance and safety, which means that the controller designed for mobile robots needs to have good transient performance and Do not violate security boundary requirements. At present, there is very little research in this area. Many control methods can only guarantee the final stability of the system, without considering the transient performance. When th...

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
IPC IPC(8): G05D1/02
CPCG05D1/0223G05D1/0214G05D1/0276
Inventor 王敏张玉望戴诗陆杨辰光
Owner SOUTH CHINA UNIV OF TECH
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