A method for acquiring an intelligent driving system test case

A technology for intelligent driving and system testing, applied in software testing/debugging, biological neural network models, etc., can solve problems such as the lack of test library formation methods, and achieve the effect of ensuring scalability

Active Publication Date: 2019-06-18
TONGJI UNIV
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no good method for forming a test library for a certain type of intelligent vehicle characteristics at present.

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 method for acquiring an intelligent driving system test case
  • A method for acquiring an intelligent driving system test case
  • A method for acquiring an intelligent driving system test case

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0023] like figure 1 As shown, the present invention relates to a method for obtaining an intelligent driving system test case, the method comprising the following steps:

[0024] Step 1: Use the perception system of the intelligent driving system to acquire pictures.

[0025] Step 2: Set up an attack target in the obtained pictures for the errors that the neural network of the intelligent driving system needs to implement.

[0026] Step 3. Determine whether the model structure of the neural network is a known structure. If so, use...

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 relates to a method for acquiring an intelligent driving system test case, and the method comprises the steps: enabling a neural network model attack problem to be formalized into an optimization problem for an image classification problem; achieving black box confrontation of the neural network model through iterative operation of an evolutionary algorithm, and meanwhile generatinga test library of the intelligent vehicle in a sample guidance mode based on the neural network confrontation. Compared with the prior art, the method can automatically obtain an effective test case library, and has the advantages of ensuring the expandability of the attack strategy while ensuring that the target model is attacked at the success rate of 100%, and the like.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to a method for acquiring test cases of an intelligent driving system. Background technique [0002] The hot development of intelligent driving is inseparable from the progress of artificial intelligence technology, and the research on neural network is the most prominent. Based on the neural network model, a real-time, high-precision, end-to-end environment perception system can be realized. But at the same time, the model also has considerable potential risks. For example, in some scenarios, some changes that are very small to humans may cause serious perception errors. How to automatically and efficiently generate effective test cases for specific models is the key to whether smart cars can be quickly implemented. [0003] For the intelligent driving unit using the neural network model, especially the perception system, the existing research on generating test sampl...

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): G06F11/36G06N3/02
Inventor 罗怡桂杨瑞嘉王逸偲沙威
Owner TONGJI UNIV
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