Vehicle following model calibration method and device, electronic equipment and storage medium

By acquiring and processing vehicle motion data, trajectory segmentation and parameter optimization, the problem of low accuracy of existing vehicle follow-up models is solved, and the accuracy and generalization capabilities of the model are improved.

CN119720533APending Publication Date: 2025-03-28XIAN JIAOTONG LIVERPOOL UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202411790453.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

The existing vehicle follow-up model has low accuracy and it is difficult to accurately simulate vehicle follow-up behavior.

Method used

By obtaining the speed of the bicycle, the relative speed of the vehicle in front and the real follow-up distance at multiple time points, the simulated follow-up distance at each time point is determined, and the trajectory segmentation is performed to obtain the vehicle follow-up model parameters corresponding to multiple trajectory segments. Enter these parameters into the pre-trained optimization model to obtain the target vehicle follow-up model parameters.

Benefits of technology

The vehicle follow-up model parameters are calibrated through two stages: trajectory segmentation and parameter optimization, which significantly improves the accuracy and generalization capabilities of the vehicle follow-up model.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a vehicle following model calibration method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring the speed of an own vehicle, the relative speed of the own vehicle and a front vehicle and a real following distance at a plurality of time points; determining a simulated car-following distance corresponding to each time point based on the self-vehicle speed, the relative speed of the front vehicle and the real car-following distance at the plurality of time points; track segmentation is carried out based on the simulated car-following distance corresponding to each time point and the real car-following distance corresponding to each time point, and vehicle car-following model parameters corresponding to a plurality of track segments are obtained; and inputting the vehicle following model parameters corresponding to the plurality of track segments into a pre-trained optimization model of the vehicle following model parameters to obtain a target vehicle following model parameter corresponding to each track segment. According to the technical scheme, the parameters of the vehicle following model are calibrated through the two stages of track segmentation and parameter optimization, and the precision of the vehicle following model is improved.
Need to check novelty before this filing date? Find Prior Art