Scene-independent unmanned driving simulation test evaluation method and device

Abstract

The embodiment of the invention discloses a scene-independent unmanned driving simulation test evaluation method and device. According to the method, for each frame of data in to-be-tested data, a safety assessment score result of the frame is obtained according to a preset RSS model, a regulatory assessment score result of the frame is obtained according to information of a traffic sign object and position information and driving information of a to-be-tested vehicle, and for each target time period in the to-be-tested data, a safety assessment score result of the frame is obtained. According to the acceleration of the to-be-tested vehicle in the target time period, calculating a comfort evaluation sub-result, carrying out a loop test on the to-be-tested data until a preset simulation frequency is reached, and sorting all the obtained evaluation sub-results to obtain a safety evaluation total result, a law evaluation total result and a comfort evaluation total result of the to-be-tested vehicle. Therefore, the data adopted for evaluation is irrelevant to the type of the scene and is not limited by the scene file of a specific type, simulation test evaluation can be carried out on any scene file, the compatibility is high, and the robustness is good.

Description

[0001] This application is a divisional application with an application date of January 11, 2021, an application number of 202110028045.X, and a divisional application titled "A Scenario-Independent Unmanned Driving Simulation Test Evaluation Method and Device" technical field [0002] The present invention relates to the technical field of unmanned driving simulation, in particular to a scene-independent unmanned driving simulation test evaluation method and device. Background technique [0003] At present, unmanned driving simulation technology is generally used in the test and evaluation of unmanned driving algorithms set for unmanned vehicles. In the process of using unmanned driving simulation technology to test and evaluate unmanned driving algorithms, it is generally necessary to use manually set scene data or use scene data collected for actual driving scenes to simulate the driving scene of the self-driving vehicle, and then carry out Simulation test evaluation. ...

AI Technical Summary

Problems solved by technology

[0004] The existing unmanned driving simulation test evaluation methods are specially designed for specific types of scene files, therefore, simulation test evaluation can only be implemented based on specific types of scene files, and are not compatible with other types of scene files. Other scene files are used for unmanned driving simulation test evaluation, and the robustness is poor

Images