The invention relates to a TCN-LSTM network-based vehicle lane changing intention identification method, which comprises the following steps of: firstly, dividing the driving intention of a target vehicle into three types of straight driving, leftward lane changing and rightward lane changing, and extracting the running state indexes of the target vehicle and corresponding surrounding adjacent vehicles from a CitySim vehicle trajectory data set by using a median filtering algorithm; and secondly, constructing a TCN-LSTM network-based vehicle lane changing intention recognition model by taking 54 indexes such as speeds, accelerations, course angles, course angle change rates and relative position information of a target vehicle and surrounding adjacent vehicles as input parameters and taking a lane changing intention of the vehicle as an output index. The lane changing intention of the vehicle is recognized by combining the vehicle speed, the acceleration and the steering angle change, the vehicle lane changing intention recognition precision is effectively improved, and the method has important significance for improving traffic safety and road section operation efficiency.
本发明涉及一种基于TCN‑LSTM网络的车辆换道意图识别方法,方法包括:首先,将目标车辆的驾驶意图分为直行、向左换道和向右换道三种类型,利用中值滤波算法从CitySim车辆轨迹数据集中提取目标车辆及对应周边相邻车辆运行状态指标。其次,以目标车辆及周边相邻车辆的速度、加速度、航向角、航向角变化率和相对位置信息等54个指标为输入参数,以车辆的换道意图为输出指标,构建了一种基于TCN‑LSTM网络车辆换道意图识别模型。本发明结合车辆速度、加速度以及转向角变化来识别车辆的换道意图,有效提高了车辆换道意图识别精度,这对于改善交通安全和提高路段运行效率具有重要的意义。
Vehicle lane changing intention recognition method based on TCN-LSTM network
一种基于TCN-LSTM网络的车辆换道意图识别方法
2024-02-06
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Urban road vehicle lane changing intention recognition system and method
European Patent Office | 2025
|Lane changing intention recognition based on speech recognition models
Online Contents | 2016
|European Patent Office | 2020
|