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

A longitudinal driving ability detection method for autonomous vehicles

A technology of automatic driving and detection method, which is applied in the direction of vehicle testing, machine/structural component testing, measuring devices, etc., which can solve the problems of lowering the trust degree of automatic driving and achieve the effect of optimal control

Active Publication Date: 2021-07-20
TONGJI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, autonomous driving has entered the stage of practical development, but it is still in the early stage of industrialization. Autonomous driving road test accidents occur from time to time. Due to safety problems caused by insufficient driving ability, the public's trust in autonomous driving has been greatly reduced. Therefore, autonomous driving vehicles It is necessary to analyze the driving ability before the application, and use the automatic driving method with high driving ability to control the self-driving car, so as to ensure the safety of autonomously coping with driving tasks in complex traffic environments

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 longitudinal driving ability detection method for autonomous vehicles
  • A longitudinal driving ability detection method for autonomous vehicles
  • A longitudinal driving ability detection method for autonomous vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] The invention provides a method for detecting longitudinal driving ability of an automatic driving vehicle, the method comprising the following steps:

[0042] Step S1: Obtain driving behavior data of heterogeneous groups, and build a longitudinal driving behavior feature library;

[0043] Step S2: Aiming at the longitudinal safety distance keeping behavior of the vehicle, use the longitudinal driving behavior feature database to construct the driving ability evaluation index system;

[0044] Step S3: Using the quantile regression method and the driving ability evaluation index system to construct a multi-factor analysis model for longitudinal driving ability;

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 present invention relates to a longitudinal driving capability detection method for autonomous vehicles, comprising: obtaining heterogeneous group driving behavior data, and constructing a longitudinal driving behavior feature library; aiming at the vehicle longitudinal safety distance keeping behavior, using the longitudinal driving behavior feature library to construct Driving ability evaluation index system; use the quantile regression method and driving ability evaluation index system to construct a multi-factor analysis model for longitudinal driving ability; obtain the operating data of autonomous driving vehicles, and use the multi-factor analysis model for longitudinal driving ability to quantitatively detect driving ability. Compared with the existing technology, it realizes the quantitative positioning of the driving ability of the self-driving car in the human driver group, and solves the problem that the existing driving ability evaluation method cannot take into account the classification and interpretability, and the evaluation results can support the self-driving car. Optimization of the control algorithm.

Description

technical field [0001] The invention relates to the field of self-driving cars, in particular to a method for detecting longitudinal driving ability of self-driving cars. Background technique [0002] Autonomous driving is an important direction for a new round of global technological innovation and industrial development. At present, autonomous driving has entered the stage of practical development, but it is still in the early stage of industrialization. Autonomous driving road test accidents occur from time to time. Due to safety problems caused by insufficient driving ability, the public's trust in autonomous driving has been greatly reduced. Therefore, autonomous driving vehicles It is necessary to analyze the driving ability before the application, and use the automatic driving method with high driving ability to control the self-driving car, so as to ensure the safety of autonomously coping with the driving task in the complex traffic environment. Contents of the in...

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): G01M17/007G06F17/15G06F17/16
CPCG01M17/007G06F17/15G06F17/16
Inventor 余荣杰龙晓捷
Owner TONGJI UNIV