Trajectory Prediction and Intention Recognition Based on CNN-GRU

Accurate trajectory prediction and intention recognition are essential for effective decision-making, as different intents manifest in distinct trajectory patterns. This study focuses on trajectory prediction and intention recognition for airborne moving targets by proposing an integrated approach t...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinghao Du, Dongdong Lu, Fei Li, Ke Liu, Xiaolan Qiu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10877792/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259260693282816
author Jinghao Du
Dongdong Lu
Fei Li
Ke Liu
Xiaolan Qiu
author_facet Jinghao Du
Dongdong Lu
Fei Li
Ke Liu
Xiaolan Qiu
author_sort Jinghao Du
collection DOAJ
description Accurate trajectory prediction and intention recognition are essential for effective decision-making, as different intents manifest in distinct trajectory patterns. This study focuses on trajectory prediction and intention recognition for airborne moving targets by proposing an integrated approach that leverages trajectory data for both tasks. Separate models were developed for trajectory prediction and intention recognition, with the trajectory prediction outcomes subsequently applied to enhance the accuracy of intention recognition. The proposed multi-channel parallel GRU-CNN neural network combines the temporal analysis capabilities of GRU with the spatial feature extraction strengths of CNN through a weight allocation strategy. This model achieved a notable performance, with a Mean Absolute Error (MAE) not exceeding 6.877. Additionally, a trajectory sequence similarity assessment system was constructed by incorporating Dynamic Time Warping (DTW), Hausdorff Distance (HD), and rate of altitude change, facilitating the classification of trajectories with similar intents. The integration of trajectory prediction into intention recognition significantly improved accuracy, as demonstrated by experimental results showing an accuracy rate exceeding 82%. These findings validate the effectiveness of the proposed method and offer an innovative technical solution for intention recognition of airborne moving targets.
format Article
id doaj-art-39ab6df20f474e06b7f68fac64724e31
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-39ab6df20f474e06b7f68fac64724e312025-08-20T01:55:53ZengIEEEIEEE Access2169-35362025-01-0113269452695710.1109/ACCESS.2025.353993110877792Trajectory Prediction and Intention Recognition Based on CNN-GRUJinghao Du0https://orcid.org/0009-0004-1379-6412Dongdong Lu1https://orcid.org/0000-0001-5965-4779Fei Li2https://orcid.org/0009-0007-7418-9415Ke Liu3https://orcid.org/0000-0002-0245-6170Xiaolan Qiu4Chinese Academy of Sciences, Aerospace Information Research Institute, Beijing, ChinaSuzhou Aerospace Information Research Institute, Suzhou, ChinaChinese Academy of Sciences, Aerospace Information Research Institute, Beijing, ChinaSuzhou Aerospace Information Research Institute, Suzhou, ChinaChinese Academy of Sciences, Aerospace Information Research Institute, Beijing, ChinaAccurate trajectory prediction and intention recognition are essential for effective decision-making, as different intents manifest in distinct trajectory patterns. This study focuses on trajectory prediction and intention recognition for airborne moving targets by proposing an integrated approach that leverages trajectory data for both tasks. Separate models were developed for trajectory prediction and intention recognition, with the trajectory prediction outcomes subsequently applied to enhance the accuracy of intention recognition. The proposed multi-channel parallel GRU-CNN neural network combines the temporal analysis capabilities of GRU with the spatial feature extraction strengths of CNN through a weight allocation strategy. This model achieved a notable performance, with a Mean Absolute Error (MAE) not exceeding 6.877. Additionally, a trajectory sequence similarity assessment system was constructed by incorporating Dynamic Time Warping (DTW), Hausdorff Distance (HD), and rate of altitude change, facilitating the classification of trajectories with similar intents. The integration of trajectory prediction into intention recognition significantly improved accuracy, as demonstrated by experimental results showing an accuracy rate exceeding 82%. These findings validate the effectiveness of the proposed method and offer an innovative technical solution for intention recognition of airborne moving targets.https://ieeexplore.ieee.org/document/10877792/Intention recognitiontrajectory predictionconvolutional neural networksgated recurrent unitstrajectory similarity
spellingShingle Jinghao Du
Dongdong Lu
Fei Li
Ke Liu
Xiaolan Qiu
Trajectory Prediction and Intention Recognition Based on CNN-GRU
IEEE Access
Intention recognition
trajectory prediction
convolutional neural networks
gated recurrent units
trajectory similarity
title Trajectory Prediction and Intention Recognition Based on CNN-GRU
title_full Trajectory Prediction and Intention Recognition Based on CNN-GRU
title_fullStr Trajectory Prediction and Intention Recognition Based on CNN-GRU
title_full_unstemmed Trajectory Prediction and Intention Recognition Based on CNN-GRU
title_short Trajectory Prediction and Intention Recognition Based on CNN-GRU
title_sort trajectory prediction and intention recognition based on cnn gru
topic Intention recognition
trajectory prediction
convolutional neural networks
gated recurrent units
trajectory similarity
url https://ieeexplore.ieee.org/document/10877792/
work_keys_str_mv AT jinghaodu trajectorypredictionandintentionrecognitionbasedoncnngru
AT dongdonglu trajectorypredictionandintentionrecognitionbasedoncnngru
AT feili trajectorypredictionandintentionrecognitionbasedoncnngru
AT keliu trajectorypredictionandintentionrecognitionbasedoncnngru
AT xiaolanqiu trajectorypredictionandintentionrecognitionbasedoncnngru