Test scene library construction method and device, electronic equipment and medium
A technology for test scenarios and construction methods, applied in the fields of artificial intelligence, autonomous driving, and autonomous parking, can solve problems such as reducing the validity and accuracy of test scenarios, and achieve the effect of reducing the number of test scenarios, improving accuracy, and avoiding construction.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0057] figure 1 It is a flowchart of a method for building a test scenario library according to the first embodiment of the present application. This embodiment is applicable to the situation of building a test scenario library for testing autonomous vehicles. The method can be constructed by a test scenario library construction device To execute, the device is implemented in the form of software and / or hardware, and is preferably configured in electronic equipment. Such as figure 1 As shown, the method specifically includes the following:
[0058] S110. Determine the scene category of the scene element; wherein, the scene category is a perception class or a strategy class.
[0059] In the specific embodiments of this application, a scene element refers to the smallest unit for constructing a scene, which is used to describe the specific content of a certain aspect of the scene, for example, the weather is sunny, the obstacle is an adult, the safety distance is 20cm, and the...
no. 2 example
[0073] figure 2 It is a flow chart of a method for building a test scenario library according to the second embodiment of the present application. On the basis of the first embodiment above, this embodiment further explains the construction of the test scenario library, and can use strategy elements Layering is performed to build test scenarios based on any combination of elements between layers. Such as figure 2 As shown, the method specifically includes the following:
[0074] S210. Perform semantic understanding on the collected scene elements; classify according to the semantic understanding of the scene elements, and determine the scene category of the scene elements.
[0075] In the specific embodiment of the present application, a large number of scene elements can be collected as much as possible through vehicles, images, vision, network and other means, and various scene elements can be converted into text information. For example, based on vehicles with normal d...
no. 3 example
[0089] Figure 4 It is a flowchart of a test scenario library construction method according to the third embodiment of the present application. On the basis of the first embodiment above, this embodiment further explains the verification of the test scenario library, and can be based on the test scenario library. Validate structure update test scenario library. Such as Figure 4 As shown, the method specifically includes the following:
[0090] S410. Determine the scene category of the scene element; wherein, the scene category is a perception category or a policy category.
[0091] S420. From the scenario elements determined by the scenario category, select strategy-type elements.
[0092] S430. Construct a test scenario library according to policy elements.
[0093] S440. Perform scenario simulation on the target test scenario in the test scenario library to verify the validity of the target test scenario.
[0094] S450. Perform a real-vehicle closed test on the self-dr...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com