Intelligent standard method and system based on automatic driving test intelligent platform car

Abstract

The invention provides an intelligent standard method based on an automatic driving test intelligent platform car, and the method comprises the following steps: step 1, building an automobile intelligent index system of the automatic driving test intelligent platform car, and analyzing the related evaluation indexes of the automatic driving test intelligent platform car; step 2, determining a network structure of a BP neural network according to an automobile intelligence standard of the automatic driving test intelligent platform vehicle; step 3, determining the number of implicit neurons; step 4, carrying out normalization non-dimensionalization processing on the data; step 5, determining the intelligent level of the automatic driving intelligent platform vehicle; and step 6, carrying out BP network training, and determining the weight range of sample indexes. According to the method, intelligent evaluation indexes are fitted based on the BP neural network, and the real values of intelligent index values can be closer to.

Description

technical field [0001] The present invention relates to the technical field of intelligent driving test, in particular to an intelligent standard method and system based on an intelligent platform vehicle for automatic driving test. Background technique [0002] A self-driving vehicle is a kind of smart car, which can also be called a wheeled automatic robot. It mainly relies on the on-board sensor system to perceive the road environment, automatically plan the driving route and control the vehicle to reach the predetermined target. [0003] In order to promote the development of unmanned vehicle technology, testing and evaluation technologies for unmanned vehicles have also begun to appear. At present, most of the evaluation tests are conducted by each research and development unit according to its own situation to perform a single index evaluation test for its single or part of the functional requirements. With the maturity of individual technologies and integrated system...

AI Technical Summary

Problems solved by technology

[0004] The evaluation and testing methods of unmanned vehicles in the prior art have a lot of human subjectivity and tendency, and the evaluation results are inaccurate

There is no classification of intelligence levels for unmanned vehicles, the evaluation results lack scientificity and accuracy, and the evaluation process does not take into account the influence of factors such as the unmanned vehicle itself, the driving environment, and human intervention

Although it can evaluate the performance of unmanned vehicles, it does not point out which specific indicators are deficient and the direction to be improved in the future, which is not conducive to the development of unmanned vehicle technology.

Images