Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (5): 1492-1499.DOI: 10.11772/j.issn.1001-9081.2020081198

Special Issue: 前沿与综合应用

• Frontier & interdisciplinary applications • Previous Articles     Next Articles

Self-generated deep neural network based 4D trajectory prediction

LI Xujuan1,2, PI Jianyong1,2, HUANG Feixiang3, JIA Haipeng3   

  1. 1. College of Computer Science and Technology, Guizhou University, Guiyang Guizhou 550025, China;
    2. Research Center of Cloud Computing and Internet of Things, Guizhou University, Guiyang Guizhou 550025, China;
    3. Guizhou Branch of CAAC Southwest Regional Administration, Guiyang Guizhou 550005, China
  • Received:2020-08-10 Revised:2020-11-19 Online:2021-05-10 Published:2020-12-09

基于自生成深度神经网络的4D航迹预测

李旭娟1,2, 皮建勇1,2, 黄飞翔3, 贾海朋3   

  1. 1. 贵州大学 计算机科学与技术学院, 贵阳 550025;
    2. 贵州大学 云计算与物联网研究中心, 贵阳 550025;
    3. 中国民用航空西南地区空中交通管理局贵州分局, 贵阳 550005
  • 通讯作者: 李旭娟
  • 作者简介:李旭娟(1987-),女,山东昌邑人,硕士研究生,主要研究方向:深度学习、数据挖掘;皮建勇(1973-),男,四川广安人,副教授,博士,CCF会员,主要研究方向:分布式计算、复杂系统、人工智能;黄飞翔(1987-),男,江苏大丰人,工程师,主要研究方向:通信、导航及监视;贾海朋(1982-),男,山东青州人,工程师,硕士,主要研究方向:通信与信息系统。

Abstract: Since 4-Dimensional (4D) trajectory prediction is not real-time and has the iterative error, an Automatically generated Conditional Variational Auto-Encoder (AutoCVAE) was proposed. It is in the form of encoding-decoding to predict the future trajectory directly, and can select observation number and prediction step flexibly. The method was guided by the preprocessed Automatic Dependent Surveillance-Broadcast (ADS-B) data, and with the reduction of the prediction error as the goal. By means of Bayesian optimization, the model structure was searched within the predefined search space. The hyper parameter values of each time were chosen by referencing the previous evaluation results, so that the structure of the new model obtained in each time was able to be closer to the target, and ultimately, a high precision 4D trajectory prediction model based on ADS-B data was completed. In the experiments, the proposed model was able to predict the trajectory quickly and accurately in real time with the Mean Absolute Error (MAE) of both latitude and longitude less than 0.03 degrees, the altitude MAE under 30 m, the time error at each time point not exceeded 10 s, and each batch trajectory prediction delay within 0.2 s.

Key words: trajectory prediction, Conditional Variational Auto-Encoder (CVAE), deep generative model, data mining, Automatic Dependent Surveillance-Broadcast (ADS-B)

摘要: 针对四维(4D)航迹预测的实时性不强和存在迭代误差的问题,提出了一种自动生成的条件变分自动编码器(AutoCVAE)。它以编码-解码的形式直接对未来一段时间的航迹进行预测,并能灵活选取观测点个数和预测步长。该方法以处理后的广播式自动相关监视(ADS-B)数据为引导,以减小预测误差为目标,通过贝叶斯优化的方法,在预定义的搜索空间内进行模型结构搜索,每一次的超参数取值都会参考之前的评估结果,使得每一次的模型结构都能向目标更靠近一点,最终实现了一个基于ADS-B数据的高精度的4D航迹预测模型。实验得出,所提模型能快速准确地进行航迹的实时预测,其中经纬度平均绝对预测误差(MAE)均小于0.03°,高度MAE小于30 m,各时刻点的时间误差也不会超过10 s,每次批量预测轨迹的延迟时间不超过0.2 s。

关键词: 航迹预测, 条件变分自动编码器, 深度生成模型, 数据挖掘, 广播式自动相关监视

CLC Number: