A deep mixture of experts network for drone trajectory intent classification and prediction using non-cooperative radar data

Simple item page
dc.contributor.authorFraser, Benjamin
dc.contributor.authorPerrusquía, Adolfo
dc.contributor.authorPanagiotakopoulos, Dimitrios
dc.contributor.authorGuo, Weisi
dc.date.accessioned2024-01-30T10:50:28Z
dc.date.available2024-01-30T10:50:28Z
dc.date.issued2024-01-01
dc.description.abstractThe intent prediction of unmanned aerial vehicles (UAVs) also known as drones is a challenging task due to the different mission profiles and tasks that the drone can perform. To alleviate this issue, this paper proposes a deep mixture of experts network to classify and predict drones trajectories measured from non-cooperative radars. Telemetry data of open-access datasets are converted to simulated radar tracks to generate a pool of heterogeneous trajectories and construct three independent datasets to train, validate, and test the proposed architecture. The network is composed of two main components: i) a deep network that predicts the class associated to the input trajectories and ii) a set of deep experts models that learns the extreme bounds of the trajectories in different future time steps. The proposed approach is tested and compared with different deep models to verify its effectiveness under different flight profiles and time-windows.en_UK
dc.identifier.citationFraser B, Perrusquía A, Panagiotakopoulos D, Guo W. (2024) A deep mixture of experts network for drone trajectory intent classification and prediction using non-cooperative radar data. In: 2023 IEEE Symposium Series on Computational Intelligence (SSCI), 5-8 December 2023, Mexico City, Mexicoen_UK
dc.identifier.eissn2472-8322
dc.identifier.issn2770-0097
dc.identifier.urihttps://doi.org/10.1109/SSCI52147.2023.10371877
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/20727
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.titleA deep mixture of experts network for drone trajectory intent classification and prediction using non-cooperative radar dataen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Drone_trajectory_intent_classification-2024.pdf
Size:
830.31 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)