Autopilot testing method and system based on mixed reality

Abstract

The invention discloses an automatic driving test method and system based on mixed reality. The method comprises the following steps: a virtual test vehicle transmits test data in a virtual environment to a vehicle terminal of a real test vehicle through a cloud server, so that the real test vehicle merges the virtual environment test data with the real environment data, and selects a driving planaccording to the merged data; the real test vehicle synchronously uploads the real-time data of a vehicle sensor to the cloud server of a control center, a road surface sensor of a test field synchronously uploads the real-time data of a road surface to the cloud server of the control center, the cloud server sends the received data to a control center calculation platform, and the control centercalculation platform updates the virtual environment according to the data provided by the cloud server and adjusts the driving speed and the driving route of the virtual test vehicle; and the control center calculation platform saves the driving parameters of the real test vehicle under the influence of the virtual test environment.

Description

Technical field [0001] The present disclosure relates to the field of automatic driving test technology, and in particular to an automatic driving test method and system based on mixed reality. Background technique [0002] The statements in this section merely improve the background art related to the present disclosure, and do not necessarily constitute prior art. [0003] With the rapid development of automobile automation and intelligence, efficient and safe autonomous driving is considered to be the form of future automobile development. Countries have carried out research and development and promotion of autonomous driving technology. my country also regards autonomous driving cars as an important part of the development of the automobile industry. Strategic Direction. The development of autonomous vehicles can promote the development of automotive-related industries such as chips, software, information communications, and data services, and develop new business models for tr...

AI Technical Summary

Problems solved by technology

The construction of traffic scenes in the closed test field is relatively limited, and it is difficult to achieve rapid changes

[0006] 2. It is difficult to accurately reproduce the scene of test failure

Closed test field test Once the test fails, the test scene is easy to change, and it is difficult to accurately reproduce the test failure scene

[0007] 3. It is difficult to conduct tests under certain extreme conditions

Testing autonomous vehicles under extreme conditions in a closed test field is risky and expensive

Especially when performing error testing, it is necessary to test the reaction of the vehicle when an error occurs, which is highly dangerous

[0008] To sum up, it is difficult to completely verify the performance of autonomous vehicles by testing in real scenarios in closed test fields alone.

Images