Modeling method of road surface type prediction model for simulating driving system

Abstract

The invention discloses a modeling method of a road surface type prediction model for simulating a driving system. The modeling method comprises the following steps of: performing a real vehicle test,and acquiring vehicle kinetic parameter data under various road surface types and various working conditions to obtain an original experiment database with road surface type identifiers; screening the original experimental database to obtain a modeling database, and training a pavement type prediction model by using a K-Means algorithm; embedding the pavement prediction model obtained by traininginto a simulated driving system; performing a real vehicle test again, collecting test data to obtain a model test database, and importing the model test database into the simulated driving system; and using a simulated driving system with a model test database to test the credibility of the pavement prediction model. According to the modeling method, the pavement type prediction model is trainedby using the K-Means algorithm on the basis of real vehicle test data, so that the problems of limitation on a complex pavement and difficulty in ensuring robustness in a using process in the prior art are solved.

Description

technical field [0001] The invention relates to a road surface type prediction model, in particular to a modeling method of a road surface type prediction model based on K-Means for simulating a driving system. Background technique [0002] Today, as cars have gradually become an integral part of people's lives, the competition in the auto industry has also intensified. How to quickly develop a car that meets customer needs has become an important issue for manufacturers in the automotive industry. With the gradual popularization and application of artificial intelligence, cars are also gradually developing in the direction of unmanned and intelligent. The simulated driving system can realize high-reliability vehicle dynamics simulation on the premise of occupying less resources, and has been adopted by most enterprises, thereby shortening the development process and reducing development costs. [0003] Road surface information is an integral part of vehicle simulation. W...

AI Technical Summary

Problems solved by technology

However, considering the complexity of the vehicle driving environment, how to set the correct road surface type for the vehicle in the simulation environment has become an engineering problem with a large workload and complicated operations

Patent CN201810584408.6 "A System and Method for Road Surface Recognition" proposes a road surface recognition method based on the physical properties of the road surface, but the method is complex to operate and has certain limitations in the identification of complex road surfaces; patent CN201810824707.2 "A Road Surface Recognition Method and Device" proposes a road surface recognition method based on image data, which is easily affected by the image data collection environment, such as care, and the robustness during use is difficult to guarantee

Images