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

Method for building intelligent driving scene library

A technology of intelligent driving and scene library, applied in the field of automobile testing, can solve the problems of fragmentation, classification and classification, etc., to achieve the effect of improving the ability of intelligent driving

Pending Publication Date: 2022-06-21
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is not yet a relatively complete test scenario library, and these test scenario libraries generally have the following shortcomings: (1) The traffic environment, human-machine co-driving, weather environment and other factors used in the intelligent driving scenario library are not clearly defined (2) Although there are clear technical methods and fields of application, there is no combination of traffic accident databases, etc., to improve requirements for intelligent driving, automatic driving to solve human driving problems, traffic accident scenarios, etc.

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
  • Method for building intelligent driving scene library
  • Method for building intelligent driving scene library
  • Method for building intelligent driving scene library

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In this specific embodiment, in step (4), a single test scenario is dynamically linked with the accident type code of the traffic accident database, and the purpose of the scenario is marked. Excluding the arrangement and combination of road traffic and natural environment, it comes from the demand when designing the scene. The demand at this time is the so-called labeling when processing the scene. Labeling is done according to the purpose of the scene. According to the single function of the intelligent driving scene, you can add ACC, AEB and other tags; at the same time, in the case of a traffic accident database, the scene can be tagged with the type of accident.

[0017] In this way, with the number of participants, motion status and physical attributes, as well as the coding of the natural traffic environment of the road, as well as the use label of the scene and the label of the accident scene, after permutation and combination, the desired scene traversal can be ...

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 method for constructing an intelligent driving scene library. The method comprises the following steps of: performing hierarchical coding on road types, road terrains, road sections, road surface types, road surface conditions, lane line types, natural weather conditions, traffic control modes and traffic flows of vehicle driving; classifying and coding the vehicle state and the vehicle man-machine co-driving state; the conditions of other participants formed by a single test scene are explained; and performing accident type labeling processing on a single test scene. Factors such as a traffic environment, man-machine co-driving and a weather environment used by an intelligent driving scene library are classified and graded, and systematic, structured and standardized scene constituent elements are formed; and in combination with a traffic accident database and scene functions, after tagging processing is carried out on the functions, the use requirements of intelligent driving, automatic driving, traffic accident scenes and the like can be inquired and managed through tags, and the method can be conveniently applied to real vehicle testing, scene simulation, accident analysis, intelligent driving ability improvement and the like.

Description

technical field [0001] The invention relates to the technical field of automobile testing, in particular to a method for building an intelligent driving scene library. Background technique [0002] At present, intelligent driving vehicles have become a hot spot in the industry, and the industry is developing rapidly. The diversity and complexity of intelligent driving vehicle test scenarios require a quantifiable scene library to represent, and more advanced automatic driving is urgently needed. Therefore, we need a general scene library for intelligent driving, which can cover simulation tests and real vehicle tests; in this way, simulation tests can cover functional and logic tests based on the scene library, relying on computing power, and widely cover test scenarios; Select scenarios and functions to form targeted tests. However, there is not yet a relatively complete test scenario library, and these test scenario libraries generally have the following deficiencies: (1)...

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 Applications(China)
IPC IPC(8): G06F11/36
CPCG06F11/3684G06F11/3696
Inventor 袁松
Owner CHONGQING CHANGAN AUTOMOBILE CO LTD