Method and device for testing perception delay performance of automatic driving vehicle

A technology for autonomous driving and test solutions, applied in the field of autonomous vehicle perception testing, can solve problems such as insufficient precision and poor execution, and achieve the effects of reducing impact, simplifying test models, and reducing background interference

Active Publication Date: 2021-11-19
北京智能车联产业创新中心有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Another object of the present invention is to provide a method for testing the perceived delay performance of an autonomous vehicle, accurately reflect the perceived delay performance of the autonomous vehicle, and solve the problems of time-consuming, poor execution, insufficient accuracy and testing problems in the traditional occlusion and shielding method. big error problem

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 and device for testing perception delay performance of automatic driving vehicle
  • Method and device for testing perception delay performance of automatic driving vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Scenario A is that the object under test and the self-driving vehicle are in a static state or a relatively static state, wherein the relatively static state means that the object under test and the self-driving vehicle have the same running speed and running direction;

[0068] For scenario A, the method of testing the perceived delay performance of autonomous driving vehicles, such as figure 2 shown, including the following steps:

[0069] S0. The self-driving vehicle includes perceptual sensors for generating perception data, and an automatic driving system for analyzing the perceptual data and outputting perceptual results, wherein the perceptual sensors include lidar, millimeter-wave radar, camera, laser radar, and millimeter-wave radar To obtain the point cloud data of the object to be measured, the camera is used to obtain the streaming media data of the object to be measured; the perception sensor is connected to the automatic driving system of the self-driving...

Embodiment 2

[0075] Scenario B is that the object to be measured and the self-driving vehicle have parallel motion directions, and when they are in the same direction, the speed of motion is different. For the above scene, the object to be measured and the self-driving vehicle are divided into the same direction and non-same direction from the direction of motion. (Facing) Two kinds, wherein, when they are in the same direction, the speed of movement of the two is further limited to be different;

[0076] Specifically, in this embodiment: scene B is specifically set to be that the self-driving vehicle and the object to be measured are parallel to each other and moving towards each other, and the driving direction along the self-driving vehicle is set as the positive direction, and m is the predetermined moving speed of the self-driving vehicle along the positive direction , n is the predetermined moving speed of the object under test along the positive direction, n is a negative value, and ...

Embodiment 3

[0086] Scenario C is that the object to be measured and the self-driving vehicle have non-parallel motion directions, that is, there is a predetermined angle between the driving route of the object to be measured and the route of the self-driving vehicle, and the predetermined angle is not 0° or 180°;

[0087] Specifically in this embodiment: scene C is specifically set such that the predetermined angle between the self-driving vehicle and the object to be measured is 35°;

[0088] For scenario C with specific settings, the method of testing the perceived delay performance of autonomous driving vehicles, such as figure 2 shown, including the following steps:

[0089] S0. The self-driving vehicle includes perception sensors for generating perception data, and an automatic driving system for analyzing the perception data and outputting perception results, wherein the perception sensors include laser radar, millimeter wave radar, camera, and laser radar and millimeter wave radar...

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 testing the sensing delay performance of an automatic driving vehicle, and the automatic driving vehicle comprises a sensing sensor used for generating sensing data, and an automatic driving system used for analyzing the sensing data and outputting a sensing result. The method comprises the following steps: S1, setting an object to be tested and an automatic driving vehicle according to a predetermined test scheme; S2, generating sensing data of the to-be-measured object through a sensing sensor; S3, selecting a reinjection sample from the sensing data, injecting the reinjection sample into the automatic driving system according to the frequency of generating the sensing data by the sensing sensor, and recording the injection starting time t1 and the time t2 of generating the first frame of correct sensing result data by the automatic driving system; and S4, calculating a value of [delta]T=t2-t1, and taking the value as the sensing delay of the automatic driving vehicle. The invention discloses a device for testing perception delay performance of an automatic driving vehicle. The method has the beneficial effect of accurately reflecting the perception delay performance of the vehicle.

Description

technical field [0001] The invention relates to the technical field of automatic driving vehicle perception testing. More specifically, the present invention relates to a method and device for testing the perceived delay performance of an autonomous driving vehicle. Background technique [0002] The perception ability of an autonomous vehicle is the core of an autonomous vehicle and a key factor in determining its ability to drive autonomously. Just like human research, drivers with symptoms of myopia, night blindness, and glaucoma (seeing blurred things) are more likely to be on the road. normal people's congress. Perception capabilities mainly include perception distance, blind spots, granularity, category, accuracy, delay and other indicators. Among them, perceptual delay is the most difficult test indicator in the industry at present, because perceptual delay is at the millisecond level, which cannot be satisfied by general test equipment. For example, the common metho...

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): G07C5/08G01S7/40G01S7/497
Inventor 党利冈
Owner 北京智能车联产业创新中心有限公司
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