首页 >

基于深度学习的融合空域空管指令语义解析技术研究(ICGNC2022推荐优秀论文)

刘鹏宇1,朱雪耀2   

  1. 1. 航空工业西安飞行自动控制研究所
    2. 中航工业西安飞行自动控制研究所
  • 收稿日期:2022-06-09 修回日期:2022-06-23 出版日期:2022-06-24 发布日期:2022-06-24
  • 通讯作者: 刘鹏宇

Semantic Parsing Technology of Air Traffic Control Instruction in Fusion Airspace Based on Deep Learning

  • Received:2022-06-09 Revised:2022-06-23 Online:2022-06-24 Published:2022-06-24
  • Contact: Peng-Yu LIU

摘要: 随着无人机技术的快速发展,无人机进入融合空域成为趋势。为提高融合空域的管控效率,对深度学习方法用于空管指令解析进行了研究。根据空管用语的特点对指令进行整理、扩充、分类和标注,编写了可用于自然语言理解模型学习的空管指令数据集。使用BiGRU-CRF模型作为深度学习的基础架构,加入注意力机制与意图反馈机制构建联合模型获取指令意图及指令参数。在空管指令数据集和ATIS数据集上的评估结果表明模型在意图识别和槽填充任务较基础架构均有近1.5%的提升,论文方法具备实用性和有效性,为无人机自然语言指控技术的发展提供有力支撑。

关键词: 融合空域, 指令解析, 深度学习, 意图识别, 槽填充, 联合模型

Abstract: With the rapid development of UAV technology, it has become a trend for UAV to enter fusion airspace. In order to improve the management and control efficiency of fusion airspace, deep learning method is applied to air traffic control instruction parsing. According to the characteristics of ATC terms, the paper sorted, expanded, classified and annotated the instructions to write an ATC instructions dataset which can be used for learning of natural language understanding model. BiGRU-CRF model is used as the infrastructure of deep learning, and attention mechanism and intention feedback mechanism are added to construct a joint model to obtain instruction intention and instruction parameters. The evaluation results on ATC instruc-tion dataset and ATIS dataset show that the model is nearly 1.5% better than the infrastructure in the task of intent identifi-cation and slot filling. The method presented in this paper is practical and effective, which provides strong support for the development of UAV natural language control technology.

Key words: fusion airspace, instruction parse, deep learning, intention recognition, slot filling, joint model

中图分类号: