Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART

The development of air traffic control (ATC) automation has been constrained by the scarcity and low quality of communication data, particularly in low-altitude complex airspace, where non-standardized instructions frequently hinder training efficiency and operational safety. This paper proposes the...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijun Pan, Boyuan Han, Peiyuan Jiang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Neurorobotics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnbot.2025.1482327/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260578609659904
author Weijun Pan
Boyuan Han
Peiyuan Jiang
author_facet Weijun Pan
Boyuan Han
Peiyuan Jiang
author_sort Weijun Pan
collection DOAJ
description The development of air traffic control (ATC) automation has been constrained by the scarcity and low quality of communication data, particularly in low-altitude complex airspace, where non-standardized instructions frequently hinder training efficiency and operational safety. This paper proposes the BART-Reinforcement Learning (BRL) model, a deep reinforcement learning model based on the BART pre-trained language model, optimized through transfer learning and reinforcement learning techniques. The model was evaluated on multiple ATC datasets, including training flight data, civil aviation operational data, and standardized datasets generated from Radiotelephony Communications for Air Traffic Services. Evaluation metrics included ROUGE and semantic intent-based indicators, with comparative analysis against several baseline models. Experimental results demonstrate that BRL achieves a 10.5% improvement in overall accuracy on the training dataset with the highest degree of non-standardization, significantly outperforming the baseline models. Furthermore, comprehensive evaluations validate the model’s effectiveness in standardizing various types of instructions. The findings suggest that reinforcement learning-based approaches have the potential to significantly enhance ATC automation, reducing communication inconsistencies, and improving training efficiency and operational safety. Future research may further optimize standardization by incorporating additional contextual factors into the model.
format Article
id doaj-art-dbd32f1c5e8d4bd3a1d4a4eb3fd815cb
institution OA Journals
issn 1662-5218
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurorobotics
spelling doaj-art-dbd32f1c5e8d4bd3a1d4a4eb3fd815cb2025-08-20T01:55:37ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182025-04-011910.3389/fnbot.2025.14823271482327Study on the standardization method of radiotelephony communication in low-altitude airspace based on BARTWeijun Pan0Boyuan Han1Peiyuan Jiang2Civil Aviation Flight University of China, Chengdu, ChinaCivil Aviation Flight University of China, Chengdu, ChinaUniversity of Electronic Science and Technology of China, Chengdu, ChinaThe development of air traffic control (ATC) automation has been constrained by the scarcity and low quality of communication data, particularly in low-altitude complex airspace, where non-standardized instructions frequently hinder training efficiency and operational safety. This paper proposes the BART-Reinforcement Learning (BRL) model, a deep reinforcement learning model based on the BART pre-trained language model, optimized through transfer learning and reinforcement learning techniques. The model was evaluated on multiple ATC datasets, including training flight data, civil aviation operational data, and standardized datasets generated from Radiotelephony Communications for Air Traffic Services. Evaluation metrics included ROUGE and semantic intent-based indicators, with comparative analysis against several baseline models. Experimental results demonstrate that BRL achieves a 10.5% improvement in overall accuracy on the training dataset with the highest degree of non-standardization, significantly outperforming the baseline models. Furthermore, comprehensive evaluations validate the model’s effectiveness in standardizing various types of instructions. The findings suggest that reinforcement learning-based approaches have the potential to significantly enhance ATC automation, reducing communication inconsistencies, and improving training efficiency and operational safety. Future research may further optimize standardization by incorporating additional contextual factors into the model.https://www.frontiersin.org/articles/10.3389/fnbot.2025.1482327/fullradiotelephony communicationair traffic controlBART modellow-altitude airspacedeep reinforcement learning
spellingShingle Weijun Pan
Boyuan Han
Peiyuan Jiang
Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
Frontiers in Neurorobotics
radiotelephony communication
air traffic control
BART model
low-altitude airspace
deep reinforcement learning
title Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
title_full Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
title_fullStr Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
title_full_unstemmed Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
title_short Study on the standardization method of radiotelephony communication in low-altitude airspace based on BART
title_sort study on the standardization method of radiotelephony communication in low altitude airspace based on bart
topic radiotelephony communication
air traffic control
BART model
low-altitude airspace
deep reinforcement learning
url https://www.frontiersin.org/articles/10.3389/fnbot.2025.1482327/full
work_keys_str_mv AT weijunpan studyonthestandardizationmethodofradiotelephonycommunicationinlowaltitudeairspacebasedonbart
AT boyuanhan studyonthestandardizationmethodofradiotelephonycommunicationinlowaltitudeairspacebasedonbart
AT peiyuanjiang studyonthestandardizationmethodofradiotelephonycommunicationinlowaltitudeairspacebasedonbart