Unlock instant, AI-driven research and patent intelligence for your innovation.

A driver's intention recognition method based on svm algorithm

A technology of driver's intention and identification method, applied in the field of driver's intention recognition based on SVM algorithm and the recognition of the driver's intention to control the operation of the vehicle, can solve problems such as difficult identification, reduce the error rate, improve vehicle safety, simplify The effect of the identification process

Inactive Publication Date: 2016-11-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The invention patent number most similar to the present invention is WLP13048, which is described in WLP13048 as a driver's intention recognition method based on a double-layer HMM (Hidden Markov Model), which is recognized only by vehicle information (such as pedals, steering wheel, etc.), In fact, it is difficult to accurately identify the driver's intentions when the vehicle information is very similar. When turning left, the driver should also make a left turn and then go straight
The vehicle information of these two intentions is very similar, and it is difficult to judge based on the vehicle information alone

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 driver's intention recognition method based on svm algorithm
  • A driver's intention recognition method based on svm algorithm
  • A driver's intention recognition method based on svm algorithm

Examples

Experimental program
Comparison scheme
Effect test

example

[0068] The total weight of the body is 1740kg, the length of the body is 5.047m, the width of the body is 1.860m, ​​the height of the body is 1.491m, the moment of inertia is 1750kgm2, the maximum torque is 270N·m, the wheelbase is 3.10m, the distance from the center of mass to the front axle is 1.25m, and the distance from the center of mass to the rear axle is The distance is 1.32m, the front wheelbase is 1.600m, the rear wheelbase is 1.626m, the center of mass height is 0.45m, and the wheel radius is 0.56m. The road surface friction coefficient is set as u=0.7, which is the normal friction coefficient of dry asphalt road. The navigator is Youlute S19 car GPS navigator.

[0069] Figure 5 It is a schematic diagram of turning left at an intersection and overtaking and changing lanes.

[0070] In this example, if Figure 5 As shown, the two situations of turning left and overtaking and changing lanes are very similar. It is difficult to judge these two situations only by ve...

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 driver's intention recognition method based on the SVM algorithm. Firstly, the type of the driver's intention is divided into categories, and then data is collected according to the divided categories, and the collected data are classified and numbered by numbers to determine the characteristic value and The category of driver intention, and then use the PCA principal component analysis method to reduce the dimensionality of the collected data, select the appropriate kernel function to map the feature vector into a high-dimensional space, so as to separate the inseparable data, and then use the pre-classified The SVM model trains the parameters and verifies the parameters offline, and finally recognizes the driver's intention through the real-time collected data. This simplifies the identification process, reduces the error rate of identification, and improves vehicle safety.

Description

technical field [0001] The invention belongs to the technical field of vehicle recognition, and more specifically, relates to a driver's intention recognition method based on an SVM algorithm, so as to realize the recognition of the driver's intention to control the vehicle. Background technique [0002] The invention patent number most similar to the present invention is WLP13048, which is described in WLP13048 as a driver's intention recognition method based on a double-layer HMM (Hidden Markov Model), which is recognized only by vehicle information (such as pedals, steering wheel, etc.), In fact, it is difficult to accurately identify the driver's intentions when the vehicle information is very similar. When turning left, the driver should also turn left and then go straight. The vehicle information of these two intentions is very similar, and it is difficult to judge based on the vehicle information alone. Contents of the invention [0003] The object of the present ...

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): B60W40/08
CPCB60W40/08
Inventor 辛晓帅王艺霖邹见效徐红兵
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA