The invention discloses a surrounding vehicle behavior recognition and trajectory prediction method based on a cyclic convolutional neural network, and belongs to the field of intelligent driving. Comprising the following steps: step 1, collecting vehicle related data according to a driving environment of an automatic driving vehicle; 2, based on the collected data set, modeling is conducted on vehicle behaviors, road environments and pedestrian/riding pedestrian behaviors, and a person-vehicle-road coupling relation model based on vector representation is constructed; 3, based on the human-vehicle-road coupling relation model, behavior pattern recognition is conducted on the target vehicle through the long-short-term memory network; and step 4, in combination with the human-vehicle-road coupling relation model and a vehicle behavior identification result, realizing trajectory prediction of the target vehicle based on a convolutional neural network. Compared with the prior art, the method has the advantages that the accuracy of behavior recognition and track prediction of surrounding vehicles by the automatic driving vehicle is effectively improved, and the efficiency and safety of driving of the automatic driving vehicle are enhanced.

    本发明公开了一种基于循环卷积神经网络的周车行为识别与轨迹预测方法,属于智能驾驶领域。包括以下步骤:步骤1:针对自动驾驶车辆行驶环境,采集车辆相关数据;步骤2:基于采集的数据集,对车辆行为、道路环境、行人/骑行人行为建模,构建基于矢量表示的人‑车‑路耦合关系模型;步骤3:基于人‑车‑路耦合关系模型,利用长短期记忆网络对目标车辆进行行为模式识别;步骤4:结合人‑车‑路耦合关系模型和车辆行为识别结果,基于卷积神经网络,实现目标车辆的轨迹预测。与现有技术相比,本发明的积极效果是:本发明有效地提高了自动驾驶车辆对周围车辆行为识别与轨迹预测的准确性,增强了自动驾驶车辆行驶的高效性与安全性。


    Access

    Download


    Export, share and cite



    Title :

    Peripheral vehicle behavior recognition and trajectory prediction method based on cyclic convolutional neural network


    Additional title:

    基于循环卷积神经网络的周车行为识别与轨迹预测方法


    Contributors:
    GAO HONGBO (author) / HE XI (author) / ZHU JUPING (author) / SHEN DA (author) / SU HUIPING (author) / XIE YUESONG (author) / YAO MAOQING (author)

    Publication date :

    2023-05-09


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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 / G06V / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Vehicle Trajectory Prediction with Convolutional Neural Network and Sequence-to-Sequence

    Kim, Hyungi / Shim, David Hyunchul | Springer Verlag | 2021


    Peripheral vehicle trajectory prediction method based on vehicle trajectory interaction dynamics

    ZHENG XUELIAN / HU XUGE / REN YUANYUAN et al. | European Patent Office | 2024

    Free access

    Convolutional neural network based vehicle turn signal recognition

    Yoneda, Keisuke / Kuramoto, Akisue / Suganuma, Naoki | IEEE | 2017


    Convolutional Social Pooling for Vehicle Trajectory Prediction

    Deo, Nachiket / Trivedi, Mohan M. | ArXiv | 2018

    Free access

    Vehicle Trajectory Prediction Model Based on Fusion Neural Network

    Mou, Xuemei / Yu, Xiang / Wang, Binbin et al. | Springer Verlag | 2023