A path tracking method for unmanned vehicles based on lssvm

An unmanned vehicle and path tracking technology, which is applied in the field of unmanned vehicle path tracking control, can solve complex work and other problems, and achieve the effects of simplified work, stable transmission time lag, and simple use

Active Publication Date: 2022-04-29
BEIHANG UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the complicated work problems caused by the path tracking controller design of the current unmanned vehicle based on the dynamic model, the present invention proposes a method for unmanned vehicle path tracking based on LSSVM. The specific technical solutions are as follows:

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 path tracking method for unmanned vehicles based on lssvm
  • A path tracking method for unmanned vehicles based on lssvm
  • A path tracking method for unmanned vehicles based on lssvm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0121] On the hardware-in-the-loop simulation experiment platform, the controller designed by the method of the present invention is used to carry out the vehicle path tracking experiment, and the tracked path is the Alt 3 Road path.

[0122] The longitudinal speed of the vehicle model is controlled by a PI controller, and the longitudinal speed is constantly changing while the vehicle is running. During the experiment, the controller command is transmitted to the steering wheel motor driver through the CAN network, and the motor driver drives the steering wheel motor to rotate, thus making the steering wheel rotate at a certain angle.

[0123] The steering wheel angle sensor transmits the angle to the controller through the CAN network, and the controller inputs the angle into the CarSim model, and the CarSim software calculates the lateral error between the vehicle model and the given path.

[0124] The controller calculates the control command again according to the lateral...

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 path tracking method for an unmanned vehicle based on LSSVM, which includes performing vehicle path tracking model LSSVM training using collected data to obtain the vehicle LSSVM path tracking model; based on the obtained LSSVM model, designing an optimal state feedback controller , the controller satisfies the actuator constraints for signal time-delay stability. The method of the present invention can solve the current unmanned vehicle path tracking controller design algorithm needs to establish a physical model, deal with nonlinear, uncertain parameters and other problems, avoiding the complicated work of the traditional controller design method based on dynamic models; device constraints and is stable against signal propagation delays.

Description

technical field [0001] The invention belongs to the technical field of unmanned vehicle control, and in particular relates to a path tracking control method of an unmanned vehicle. Background technique [0002] Path-following control is an important part of unmanned vehicles to achieve automatic driving. Existing path-following control methods include model predictive control methods, sliding mode control methods, and methods based on analysis of stable conditions such as state feedback and output feedback, and most of these methods are based on vehicle dynamics models. Therefore, when using these methods to design a controller, it is necessary to establish a vehicle dynamics model first. However, the vehicle dynamics model is nonlinear, which often incorporates some noise, uncertain parameters, and time-varying parameters. Controller design work on this basis presents difficulties. In order to achieve precise control, modeling and controller design work will become very c...

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): G05B13/04
CPCG05B13/042
Inventor 张辉石谦
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