Construction method of automatic driving test scene and difficulty coefficient calculation method thereof

Abstract

The invention relates to a construction method of an automatic driving test scene and a difficulty coefficient calculation method thereof. Firstly, a test scene hierarchical structure framework is established in sequence. A structural framework at least comprises four layers, namely a first layer, a second layer and a third layer, the system comprises a target layer, a dimension layer, a categorylayer and an element layer, the target layer comprises at least four dimensions. Each dimension comprises a plurality of categories, each category comprises a plurality of elements, a target scene tobe constructed is determined according to the target layer, the categories are sequentially determined under the dimensions, required specific elements are selected from the categories, and finally the target test scene is constructed. Weights are given to different levels of elements in each dimension, element matching is carried out on a scene to be constructed, and calculation of the scene testdifficulty coefficient is completed. The invention fills up the blank in the field of the current automatic driving test scene construction method, provides a test difficulty level evaluation methodfor the constructed scene, and formulates test schemes for each function test item.

Description

technical field [0001] The invention relates to the field of automatic driving vehicle testing, in particular to a method for constructing an automatic driving test scene and a method for calculating the difficulty coefficient of the test. Background technique [0002] Autonomous driving technology can effectively alleviate traffic congestion and reduce the incidence of traffic accidents. It is one of the hotspots in the field of intelligent transportation systems and artificial intelligence. At present, many related enterprises or scientific research institutions at home and abroad are vigorously developing autonomous driving technology, which has made remarkable progress in the feasibility and practical application of this technology. Among them, some manufacturers have developed an intelligent network with L3 automatic driving capability. connected car. [0003] With the rapid development of automatic driving technology at home and abroad, some problems have been gradual...

AI Technical Summary

Problems solved by technology

Compared with the development of autonomous driving technology, the testing and evaluation industry of autonomous vehicles is still in its infancy, and there is still a lack of systematic theoretical research and support in the selection, collocation and construction of test roads, resulting in a relatively random selection of test roads; in addition, Demonstration areas at home and abroad lack uniform standards in the formulation of test scenarios and difficulty evaluation of typical test scenarios for vehicles of various autonomous driving levels

Images