Automatic test behavior generation method and server

Abstract

The invention provides an automatic test behavior generation method. The automatic test behavior generation method comprises the steps that a server analyzes data of scenes in a database to obtain problem scenes; the server stores the problem scene into a scene demand library; the server generates a test task according to the problem scene in the scene demand library; the server distributes the test task to the automatic equipment; the automatic equipment obtains a target place which can be used for testing according to the test task and the high-precision map; the automatic device obtains test data at a destination. The invention further provides a server applying the automatic test behavior generation method. According to the method for generating the automatic test behavior, the effect of automatically generating the test task of the automatic equipment is achieved by combing and perfecting the data in the database.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to a method and server for generating automatic test behaviors. Background technique [0002] With the development of society, self-driving vehicles have entered all aspects of human life and play a huge role. Since most of the behaviors of automatic equipment are determined by computers, the determination of the behavior of automatic equipment needs to analyze a large amount of data, and calculate the behavior instructions of automatic equipment according to the analysis results. For example, for autonomous vehicles, a large amount of invalid data will be generated during the process of obtaining actual road test data and simulation data by autonomous vehicles, such as data duplication and missing data. These invalid data will lead to errors in the data analysis of the self-driving vehicle, which will cause errors in the path planning of the self-driving vehicle, which is a very d...

AI Technical Summary

Problems solved by technology

These invalid data will lead to errors in the data analysis of the self-driving vehicle, making the path planning of the self-driving vehicle wrong, which is a very dangerous situation

If manual processing deletes these data and adds test tasks based on existing data, it is a very heavy workload, and the efficiency is low, and it cannot meet the real-time information requirements of self-driving vehicles in some cases.

Images