LSTM-based lane change prediction using Waymo open motion dataset: The role of vehicle operating space

作     者：Xing Fu Jun Liu Zhitong Huang Alex Hainenand Asad J.Khattak 

作者机构：Department of CivilConstruction and Environmental EngineeringThe University of AlabamaTuscaloosaAL 35487USA LeidosInc.RestonVA 20190USA Department of Civil and Environmental EngineeringThe University of TennesseeKnoxvilleTN 37916USA 

出 版 物：《Digital Transportation and Safety》 (数字交通与安全（英文）)

年 卷 期：2023年第2卷第2期

页      面：112-123页

学科分类：08[工学] 082303[工学-交通运输规划与管理] 082302[工学-交通信息工程及控制] 0823[工学-交通运输工程] 

主　　题：Long Short-Term Memory Lane change prediction Vehicle Operating Space Waymo open data Sensitivity analysis 

摘      要：Lane change prediction is critical for crash avoidance but challenging as it requires the understanding of the instantaneous driving *** cutting-edge artificial intelligence and sensing technologies,autonomous vehicles(AVs)are expected to have exceptional perception systems to capture instantaneously their driving environments for predicting lane *** exploring the Waymo open motion dataset,this study proposes a framework to explore autonomous driving data and investigate lane change *** the framework,this study develops a Long Short-Term Memory(LSTM)model to predict lane changing *** concept of Vehicle Operating Space(VOS)is introduced to quantify a vehicle s instantaneous driving environment as an important indicator used to predict vehicle lane *** examine the robustness of the model,a series of sensitivity analysis are conducted by varying the feature selection,prediction horizon,and training data balancing *** test results show that including VOS into modeling can speed up the loss decay in the training process and lead to higher accuracy and recall for predicting lane-change *** study offers an example along with a methodological framework for transportation researchers to use emerging autonomous driving data to investigate driving behaviors and traffic environments.