학술논문
基于多级阈值的车辆换道预测方法 / Vehicle Lane Changing Prediction Method Based on Multi-Level Threshold
Document Type
Academic Journal
Author
Source
自动化应用 / Automation Application. 65(1):32-34
Subject
Language
Chinese
ISSN
1674-778X
Abstract
车辆换道行为是机动车在道路行驶时的一种常见行为,对其进行预测能有效减少交通事故.为准确预测目标车辆换道行为,根据车辆在时间内的横向位移,提出基于多阈值的车辆换道预测方法.该方法根据法规,结合车速设置换道时的横向位移阈值、方向盘转角与转速阈值,探索多阈值间的相互作用关系,通过多阈值协同预测驾驶员换道意图.结果表明,系统的预判准确率可达95%以上,说明该方法能准确预测车辆换道意图,且实时性较好,能为辅助驾驶技术的发展提供一定参考.
Vehicle lane changing behavior is a common behavior of motor vehicles while driving on the road,and predicting it can effectively reduce traffic accidents.To accurately predict the lane changing behavior of the target vehicle,a multi threshold based vehicle lane changing prediction method is proposed based on the lateral displacement of the vehicle over time.This method is based on regulations and combines the lateral displacement threshold,steering wheel angle,and speed threshold when changing lanes at vehicle speed.It explores the interaction relationship between multiple thresholds and predicts the driver's intention to change lanes through collaborative prediction of multiple thresholds.The results show that the prediction accuracy of the system can reach over 95%,indicating that the method can accurately predict the vehicle's intention to change lanes and has good real-time performance,which can provide a certain reference for the development of assisted driving technology.
Vehicle lane changing behavior is a common behavior of motor vehicles while driving on the road,and predicting it can effectively reduce traffic accidents.To accurately predict the lane changing behavior of the target vehicle,a multi threshold based vehicle lane changing prediction method is proposed based on the lateral displacement of the vehicle over time.This method is based on regulations and combines the lateral displacement threshold,steering wheel angle,and speed threshold when changing lanes at vehicle speed.It explores the interaction relationship between multiple thresholds and predicts the driver's intention to change lanes through collaborative prediction of multiple thresholds.The results show that the prediction accuracy of the system can reach over 95%,indicating that the method can accurately predict the vehicle's intention to change lanes and has good real-time performance,which can provide a certain reference for the development of assisted driving technology.