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!
Description
Summary: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.
ISSN:2169-3536