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

Vehicle driving behavior predicating method based on machine learning

A vehicle driving and machine learning technology, applied in the field of Internet of Vehicles, can solve problems such as insufficient relationship mining

Active Publication Date: 2018-09-18
TONGJI UNIV
View PDF6 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the existing vehicle driving behavior prediction model is insufficient in mining the relationship between vehicle body attributes, road information, and driving environment and driving behavior, the present invention comprehensively considers important influencing factors such as vehicle attributes, road information, and driving environment, and proposes a method based on Vehicle Driving Behavior Prediction Method Based on Machine Learning

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
  • Vehicle driving behavior predicating method based on machine learning
  • Vehicle driving behavior predicating method based on machine learning
  • Vehicle driving behavior predicating method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0110] The concrete implementation process of the present invention is as image 3 As shown, it includes the following four aspects:

[0111] ①Definition of vehicle features, road features, and vehicle driving environment features

[0112] ② Vehicle displacement prediction model

[0113] ③Vehicle driving behavior prediction model

[0114] ④Vehicle driving behavior prediction method

[0115] Step 1, define a feature set, including vehicle feature definition, road feature definition, and vehicle driving environment feature definition.

[0116]Step 11, vehicle feature definition

[0117] Vehicle features include body length L, body width W, vehicle speed, acceleration, current driving direction, and turning action at intersections, where the vehicle speed and acceleration at time t are marked as v(t) and a(t) respectively, and the rest of the features are defined as follows :

[0118] Definition 1. Vehicle driving direction vDir(t), which represents the vehicle’s moving dir...

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

A vehicle driving behavior predicating method based on machine learning relates to the field of Internet-of-vehicles. The invention aims to utilize machine learning technology for mining a relation among vehicle attribute, road information, driving environment information and a vehicle driving behavior, thereby improving accuracy in predicating the vehicle driving behavior. The method comprises the following steps of 1, defining a characteristic set: defining a vehicle characteristic, defining a road characteristic and defining a vehicle driving environment; 2, operating a vehicle displacementpredicating model, performing characteristic extraction and data preprocessing, extracting a distance characteristic between the vehicle and a front crossing, extracting a crossing allowed turning action characteristic, and extracting a label; operating a vehicle displacement predicating model, defining a training sample set, and training the vehicle displacement predicating model; 3, operating avehicle driving behavior predicating model, and defining a Gaussian component; and 4, predicating the vehicle driving behavior.

Description

technical field [0001] The invention relates to the field of Internet of Vehicles, in particular to a method for predicting vehicle driving behavior based on machine learning. Background technique [0002] Vehicle driving behavior prediction mainly serves applications related to the safety of the Internet of Vehicles, such as vehicle anti-collision monitoring at intersections. The existing research on vehicle driving behavior prediction mainly considers the historical behavior trajectory of the vehicle and the road condition information of the vehicle. These studies idealize the modeling of vehicles and road conditions, ignoring the vehicle's own attributes (such as body length and width), the distance from the vehicle to the intersection, traffic signals and lane turning permission signs and other important factors that affect vehicle driving behavior, resulting in There is a large deviation between the prediction results of driving behavior on real urban roads and the act...

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): G08G1/16B60W40/08G06K9/62G06N3/08
CPCG06N3/084G08G1/16B60W40/08G06F18/23
Inventor 程久军任思宇
Owner TONGJI 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