A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios
Abstract Trajectory prediction of the ego vehicle is necessary for the cooperation driving of intelligent vehicles and drivers. Methods based on deep learning can fit complex functions, but they usually focus on vehicles' behavioral characteristics. However, vehicles' trajectories are clos...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-08-01
|
Series: | IET Intelligent Transport Systems |
Subjects: | |
Online Access: | https://doi.org/10.1049/itr2.12345 |
_version_ | 1797739575974559744 |
---|---|
author | Shanshan Xie Jiachen Li Jianqiang Wang |
author_facet | Shanshan Xie Jiachen Li Jianqiang Wang |
author_sort | Shanshan Xie |
collection | DOAJ |
description | Abstract Trajectory prediction of the ego vehicle is necessary for the cooperation driving of intelligent vehicles and drivers. Methods based on deep learning can fit complex functions, but they usually focus on vehicles' behavioral characteristics. However, vehicles' trajectories are closely related to the cognition results of drivers. Therefore, based on drivers' cognitive characteristics, a network model is designed to predict vehicle trajectories. Specifically, in the perception stage, featured grids are used that are in the driver's view to encode perceptual information; in the decision stage, convolution and graph attention operations are combined to model the driver's interaction with the surrounding traffic elements; in the motion stage, the elements are constrained in one hidden layer by vehicles' actual control inputs and design the corresponding method to obtain probabilistic results. With experiments in two typical scenarios, including intersection and roundabout, the proposed method can obtain reasonable prediction accuracy and generalizability. Meanwhile, abundant experiments are conducted and the results are compared, which reveal some common problems when predicting vehicle trajectories, particularly based on drivers' cognitive characteristics. These lessons learned from this study are summarized which may be useful for newcomers. |
first_indexed | 2024-03-12T14:00:10Z |
format | Article |
id | doaj.art-cb2268e8bd4c477ba9a92b9629df84e0 |
institution | Directory Open Access Journal |
issn | 1751-956X 1751-9578 |
language | English |
last_indexed | 2024-03-12T14:00:10Z |
publishDate | 2023-08-01 |
publisher | Wiley |
record_format | Article |
series | IET Intelligent Transport Systems |
spelling | doaj.art-cb2268e8bd4c477ba9a92b9629df84e02023-08-22T07:47:26ZengWileyIET Intelligent Transport Systems1751-956X1751-95782023-08-011781544155910.1049/itr2.12345A cognition‐inspired trajectory prediction method for vehicles in interactive scenariosShanshan Xie0Jiachen Li1Jianqiang Wang2State Key Laboratory of Automotive Safety and Energy Tsinghua University Beijing ChinaUniversity of California, Berkeley Berkeley California USAState Key Laboratory of Automotive Safety and Energy Tsinghua University Beijing ChinaAbstract Trajectory prediction of the ego vehicle is necessary for the cooperation driving of intelligent vehicles and drivers. Methods based on deep learning can fit complex functions, but they usually focus on vehicles' behavioral characteristics. However, vehicles' trajectories are closely related to the cognition results of drivers. Therefore, based on drivers' cognitive characteristics, a network model is designed to predict vehicle trajectories. Specifically, in the perception stage, featured grids are used that are in the driver's view to encode perceptual information; in the decision stage, convolution and graph attention operations are combined to model the driver's interaction with the surrounding traffic elements; in the motion stage, the elements are constrained in one hidden layer by vehicles' actual control inputs and design the corresponding method to obtain probabilistic results. With experiments in two typical scenarios, including intersection and roundabout, the proposed method can obtain reasonable prediction accuracy and generalizability. Meanwhile, abundant experiments are conducted and the results are compared, which reveal some common problems when predicting vehicle trajectories, particularly based on drivers' cognitive characteristics. These lessons learned from this study are summarized which may be useful for newcomers.https://doi.org/10.1049/itr2.12345cognition‐inspired methodgridlearning‐based methodvehicle trajectory prediction |
spellingShingle | Shanshan Xie Jiachen Li Jianqiang Wang A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios IET Intelligent Transport Systems cognition‐inspired method grid learning‐based method vehicle trajectory prediction |
title | A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios |
title_full | A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios |
title_fullStr | A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios |
title_full_unstemmed | A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios |
title_short | A cognition‐inspired trajectory prediction method for vehicles in interactive scenarios |
title_sort | cognition inspired trajectory prediction method for vehicles in interactive scenarios |
topic | cognition‐inspired method grid learning‐based method vehicle trajectory prediction |
url | https://doi.org/10.1049/itr2.12345 |
work_keys_str_mv | AT shanshanxie acognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios AT jiachenli acognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios AT jianqiangwang acognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios AT shanshanxie cognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios AT jiachenli cognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios AT jianqiangwang cognitioninspiredtrajectorypredictionmethodforvehiclesininteractivescenarios |