A method and related device for displacement filling modeling

Abstract

The present application discloses a method and device for displacement filling modeling, the method includes: the relative displacement s between multiple groups of other vehicles and the target vehicle obtained by identifying and obtaining based on historical point cloud data corresponding to multiple other vehicles c , relative velocity v c and the corresponding calculation time t c , the regression modeling obtains the first displacement filling model; the coefficient of determination R based on the first displacement filling model 2 and the preset coefficient of determination value to determine the target displacement filling model. It can be seen that based on the relative displacement s of multiple groups of other vehicles and the target vehicle c , relative velocity v c and the corresponding calculation time t c , the target displacement filling model obtained by regression modeling is used to achieve displacement filling. The point cloud data can more accurately predict the relative displacement of other vehicles and the target vehicle through the target displacement filling model, reduce the delay difference, and avoid inaccurate lag. question.

Description

technical field [0001] The present application relates to the technical field of vehicle data analysis, in particular to a displacement filling modeling method and a related device. Background technique [0002] When driving a vehicle, especially unmanned driving, it is necessary to clarify the relative displacement of other vehicles and the own vehicle. At present, the self-vehicle generally obtains the relative displacement of other vehicles and the self-vehicle through the point cloud recognition of the lidar. Specifically, the point cloud data corresponding to other vehicles is input into the point cloud recognition algorithm, and the output is obtained to obtain the relative displacement of other vehicles and the self-vehicle. [0003] However, the inventor found through research that the point cloud recognition algorithm requires a certain amount of computing time, and during the calculation process of the point cloud recognition algorithm, the own vehicle and other ve...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found through research that the point cloud recognition algorithm requires a certain amount of computing time, and during the calculation process of the point cloud recognition algorithm, the self-vehicle and other vehicles still continue to move, the other vehicles obtained by the point cloud recognition algorithm and the self-vehicle There is a certain delay difference between the relative displacement and the actual relative displacement, that is, the relative displacement between other vehicles and the self-vehicle obtained by the point cloud recognition algorithm has the problem of lag and inaccuracy

Images