Vehicle track prediction model determination method and device and storage medium
By using multiple sets of candidate training data to train and test the vehicle trajectory prediction model, the target model that meets the preset accuracy conditions is determined, which solves the problem of low accuracy in trajectory prediction in the prior art, and improves the accuracy of judging trajectory and driving experience.
CN119961598APending Publication Date: 2025-05-09CHONGQING CHANGAN TECH CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202510027473.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-08
- Publication Date
- 2025-05-09
AI Technical Summary
Technical Problem
In the prior art, the accuracy of the trajectory prediction algorithm for the plugged scene is low, resulting in the vehicle's judgment of whether the vehicle is plugged in other lanes is not accurate enough, affecting the driving experience.
Method used
By acquiring multiple sets of candidate training data, including real data and simulated plug data, the vehicle trajectory prediction model is trained and tested, and the target model that meets the preset accuracy conditions is determined to improve the accuracy of trajectory prediction.
Benefits of technology
It improves the accuracy of the vehicle's prediction of the trajectory of the scrambled scene, enhances the ability to judge whether vehicles in other lanes are plugged, and improves the driving experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119961598A_ABST
Abstract
The invention relates to the technical field of automobiles, in particular to the technical field of trajectory prediction, and particularly relates to a method and device for determining a vehicle trajectory prediction model and a storage medium. The method at least solves the technical problem that the driving experience is affected due to the fact that the vehicle cannot accurately judge whether vehicles on other lanes are plugged or not due to the fact that the accuracy of a trajectory prediction algorithm of the vehicle for a plugging scene is low in the prior art. The method comprises the steps that multiple sets of candidate training data are acquired, a trained vehicle trajectory prediction model is trained based on the multiple sets of candidate training data, multiple candidate models are obtained, and one candidate model corresponds to one set of candidate training data. And testing the plurality of candidate models to obtain a plurality of test results which are used for reflecting the accuracy of vehicle trajectory prediction. And based on the plurality of test results, determining a target model from the plurality of candidate models, the target model being a candidate model whose test result satisfies a preset accuracy condition.
Need to check novelty before this filing date? Find Prior Art