A calculation method for the complexity of traffic participants in autonomous driving test scenarios
A test scenario and automatic driving technology, which is applied in traffic flow detection, traffic control system, road vehicle traffic control system, etc., can solve the problems of poor horizontal comparability of dynamic traffic participant test scenarios and lack of unified standards for evaluation, so as to promote Iterative updates, accelerated landing, and reasonable calculation effects
Active Publication Date: 2021-09-03
TONGJI UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, the current evaluation of autonomous driving test scenarios lacks a unified standard, which includes the evaluation of the complexity of typical test scenarios of autonomous vehicles, especially the related research on the complex quantification methods of dynamic traffic participants in the test scenarios, resulting in different parameters. The horizontal comparability of dynamic traffic participants and test scenarios under the configuration is poor
Therefore, the complex quantification of dynamic traffic participants in autonomous driving test scenarios is a major gap in the field.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0100] In this embodiment, the types of traffic participants in the test scene include cars (car) and buses (bus), and the dynamic parameter thresholds for determining the two are respectively:
[0101] car dynamics parameter threshold R car =(-7.5,6.9), threshold value of bus dynamic parameters, R bus =(-6.0,4.0).
[0102] The initial state parameter configurations of the two vehicles are the same, specifically:
[0103] S 0 = 0;
[0104] a 0 =0.5; (ms -2 )
[0105] v 0 =15; (ms -1 )
[0106] Then, according to the calculation based on the initial state of the vehicle and the dynamic threshold range, the final longitudinal position of the car for full deceleration is 15, and the final longitudinal position for full acceleration is 162, so the sampling distance set S of the car is car ={16,17,…,162}, the same as the sampling distance set S of the bus bus ={19,20,...,125}.
[0107] The optimal longitudinal control quantity corresponding to each sampling distance is ob...
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
Login to View More Abstract
The present invention relates to a method for calculating the complexity of traffic participants in an automatic driving test scene, comprising the following steps: S1: Acquiring the dynamic parameter threshold R of all types of traffic participants in the test scene type ; S2: According to the initial state of each traffic participant and the dynamic parameter threshold R type , calculate the corresponding longitudinal sampling distance set S type ; S3: Obtain the longitudinal sampling distance set S by optimizing the search algorithm type The optimal longitudinal control amount corresponding to each sampling distance in ; S4: According to the sampling distance and the optimal longitudinal control amount, calculate the reachable domain Ω of each traffic participant within the prediction time t type ; S5: According to the reachable domain Ω of each traffic participant type Computing the complexity H of the traffic participants in the test scene, compared with the prior art, the present invention provides a basis for the state and parameter design of the dynamic traffic participants in the automatic driving test scene, and has the advantages of improving the test efficiency of the automatic driving vehicle.
Description
technical field [0001] The invention relates to the field of testing and evaluation in automatic driving vehicle technology, in particular to a calculation method for the complexity of traffic participants in an automatic driving test scene. Background technique [0002] In recent years, autonomous vehicle technology has become one of the current research hotspots, both in academia and industry. However, with the rapid development of autonomous driving technology, the frequent occurrence of dangerous accidents has gradually highlighted some safety-oriented issues. One of the means of solving these problems is to conduct accurate, sufficient and complete testing of self-driving cars. A complete test process, including after multiple tests on the tested object in the same environment, quantifies the test results with standard evaluation indicators, and then feeds back to the test scenario designer; the designer evaluates the test scenario according to the evaluation results ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/01G06F30/20
CPCG08G1/0104G08G1/0129G06F30/20
Inventor 陈君毅张灵童马依宁邢星宇吴旭阳熊璐
Owner TONGJI UNIV