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

Verification method, platform and storage medium for expected functional safety of autonomous driving algorithms

A technology of automatic driving and expected functions, which is applied in the direction of motor vehicles, non-electric variable control, two-dimensional position/channel control, etc., can solve the problems such as the lack of comprehensive guarantee of the safety of test and verification results and the lack of the underlying execution system. , to achieve the effect of improving safety

Active Publication Date: 2020-08-21
ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to propose a verification method, platform and storage medium for the expected functional safety of the autonomous driving algorithm, aiming at solving the problem that the prior art test verification scheme for autonomous driving lacks an underlying execution system and can only be controlled at the virtual level. The security of the test and verification results cannot be fully guaranteed

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
  • Verification method, platform and storage medium for expected functional safety of autonomous driving algorithms
  • Verification method, platform and storage medium for expected functional safety of autonomous driving algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] see figure 1 : This embodiment proposes a method for verifying the expected functional safety of an automatic driving algorithm, and the method specifically includes the following steps:

[0039] S1. Establish an automatic driving function algorithm in the visual simulation tool Matlab / Simulink software, and establish a virtual automatic driving scene corresponding to the automatic driving function algorithm through a virtual scene modeling software (such as Prescan);

[0040] S2. The vehicle dynamics simulation software Carsim establishes the real vehicle dynamics model, and runs it in the hardware dSPACEScalexio system;

[0041] S3. Realize rapid prototyping of the automatic driving function algorithm established in the visual simulation tool Matlab / Simulink software in the hardware dSPACE MicroAutoBox;

[0042] S4. Collect the obstacle information provided in the upper layer virtual scene modeling software Prescan scene through the hardware MicroAutoBox and receive ...

Embodiment 2

[0053] In addition, to achieve the above purpose, see figure 2 : This embodiment also proposes a verification platform for the expected functional safety of the autonomous driving algorithm, including a host computer, a domain controller dSPACE MicroAutoBox, a lower computer dSPACE Scalexio, and a bottom execution system;

[0054] The upper computer runs the PreScan software and the man-machine interface. The PreScan software is used to provide a virtual driving interface similar to the real test conditions and receive sensor information provided by the autonomous driving millimeter-wave radar and camera environment perception module;

[0055] The domain controller dSPACE MicroAutoBox receives various sensor signals provided by the host computer through the CAN line, performs information fusion to obtain information such as the vehicle speed and position of the target obstacle, and then sends braking, Steering and throttle signal commands;

[0056] The lower computer dSPACE ...

Embodiment 3

[0062] In addition, in order to achieve the above purpose, this embodiment also proposes a storage medium, the storage medium stores a verification program for the expected functional safety of the automatic driving algorithm, and when the verification program for the expected functional safety of the automatic driving algorithm is executed by the processor Steps for realizing the verification method for the expected functional safety of the autonomous driving algorithm described above.

[0063] The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

[0064] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implement...

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, platform and storage medium for verifying the expected functional safety of an automatic driving algorithm, which includes: establishing an automatic driving function algorithm in Matlab / Simulink software, and establishing a corresponding virtual version of the automatic driving function algorithm through virtual scene modeling software. Autonomous driving scenario; a real vehicle dynamics model is established by Carsim and run in the hardware dSPACE Scalexio system; the automatic driving function algorithm established in the Matlab / Simulink software is quickly prototyped in the hardware dSPACE MicroAutoBox; the above closed-loop control process forms a Autonomous driving HIL test system, in which virtual modeling is performed based on SOTIF hazardous scenarios, and the autonomous driving function algorithm in dSPACE MicroAutoBox is verified by SOTIF MIL and HIL.

Description

technical field [0001] The invention relates to the technical field of automobiles, in particular to a verification method, platform and storage medium for the expected functional safety of an automatic driving algorithm. Background technique [0002] Self-driving vehicle simulation testing and verification is an indispensable process in the entire system development process, which is more important than the simulation, testing and verification methods of traditional automobile self-driving cars. Because the automatic driving system cannot fully identify and effectively deal with the complexity of the environment, only through a large number of simulations, tests to find problems, and optimize the solutions to the found problems can promote the mass production and launch of autonomous driving vehicles. [0003] At present, some scientific research institutes have proposed test and verification schemes for autonomous driving. Among them, the upper-level automatic driving vir...

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): G05D1/02
CPCG05D1/0246G05D1/0257G05D1/0214G05D1/0221G05D1/0285
Inventor 姜建满崔玉顺吴琼岳丽姣时利张一营徐毅林徐春梅
Owner ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD
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