Volume 52 Issue 12
Dec.  2023
Turn off MathJax
Article Contents
Article Navigation >  Infrared and Laser Engineering  > 2023  >  52(12): 20230183

Liu Wanqing, Wei Guo, Gao Chunfeng, Yu Xudong, Tan Zhongqi, Zhang Chengzhong, Hou Chengzhi, Zhu Xu. Deep learning-based impact mitigation method for UWB NLOS propagation[J]. Infrared and Laser Engineering, 2023, 52(12): 20230183. doi: 10.3788/IRLA20230183
Citation: Liu Wanqing, Wei Guo, Gao Chunfeng, Yu Xudong, Tan Zhongqi, Zhang Chengzhong, Hou Chengzhi, Zhu Xu. Deep learning-based impact mitigation method for UWB NLOS propagation[J]. Infrared and Laser Engineering, 2023, 52(12): 20230183. doi: 10.3788/IRLA20230183
shu

Deep learning-based impact mitigation method for UWB NLOS propagation

doi: 10.3788/IRLA20230183
  • 1.

    College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China

  • 2.

    Nanhu Laser Laboratory, National University of Defense Technology, Changsha 410073, China

  • 3.

    College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China

  • Received Date: 2023-04-10
  • Rev Recd Date: 2023-05-10
    • Available Online: 2023-12-22
  • Publish Date: 2023-12-22
  •   Objective  With the continuous development of intelligent technologies and devices, precise positioning technology in the military field is becoming increasingly widespread, and its application scenarios cover both outdoor and indoor environments. Global Navigation Satellite System (GNSS) positioning technology is commonly used for its high positioning accuracy and rich information provision in outdoor environments; However, its positioning accuracy in indoor environments is significantly reduced due to the obstruction of walls and other obstacles. Ultra-Wideband (UWB) technology shows obvious advantages with its high positioning accuracy, firm spatial and temporal resolution, fast transmission rate, and low cost. These advantages make UWB technology particularly suitable for indoor high-precision positioning. In the indoor environment, various obstacles block the propagation channel between the base station and the tag of the UWB system, due to the Non-Line-Of-Sight (NLOS) phenomenon of UWB signals, the positioning accuracy of UWB systems is significantly reduced. Therefore, it is necessary to research the impact mitigation method for UWB NLOS propagation.   Methods  A deep neural network based on deep learning techniques is proposed for UWB NLOS propagation impact mitigation. This deep neural network takes the initial channel impulse response (CIR) of the UWB device as input and the ranging error of the UWB device as output. The experimental analysis shows that the characteristics of CIR data are significantly different under LOS and NLOS propagation conditions (Fig.7), which provides a solid theoretical basis for establishing the mapping relationship between CIR and ranging error using deep learning methods. Meanwhile, the network performance is related to the dimensionality of the input CIR data. The network performance is best when the input CIR data is 128 dimensions (Fig.8). When the input of the deep neural network is 128-dimensional data, too long input will lead to the structural design of the network becoming difficult. And the number of network layers is too small, the network performance can not meet the requirements to achieve good NLOS propagation impact mitigation effect; After the number of network layers increases to a certain degree, the network performance will decrease with the increase of the number of layers. For this reason, the ResNet network is selected in this paper, which enables the gradient to flow effectively to the early layers near the input layer by introducing residual connections in the deep neural network, thus improving the network performance with the increase of layers. At the same time, CIR data, as a time-series signal, correlates its data points. The global features of CIR data must be considered, while local module such as convolution can only extract local features. For this reason, this paper introduces the Non-local module, which can capture the long-distance dependence between locations and extract global information. In summary, the proposed deep neural network is constructed by inserting the Non-local module into the ResNet network's basic module while considering the CIR data's features, and named the deep neural network as NLO-ResNet.   Results and Discussions   In order to evaluate the NLOS propagation impact mitigation performance of the proposed deep neural network, four networks were selected for performance comparison. Four networks include two machine learning-based networks, SVM and MLP, and two deep learning-based networks, CNN and ResNet. Experimental results (Tab.1) show that, due to the increase in the number of layers of the network and the change in the input data, the performance of the deep learning-based network is generally better than that of the machine learning-based network; Among the deep learning-based networks, the CNN network has the worst performance, the ResNet network improves with the increase of the number of layers due to the introduction of residual connections, and the NLO-ResNet network has the best performance, which has the most comprehensive feature extraction of the input CIR data. The mean absolute error (MAE) is reduced by 12.2% compared to the CNN-based network and 4.8% compared to the ResNet-based network, and the learning process of this network converges quickly (Fig.10), and the predicted range error of this network is very close to the actual range error (Fig.11).   Conclusions  To improve the accuracy of UWB systems under NLOS propagation conditions, a deep learning-based NLOS propagation impact mitigation method is proposed, which constitutes a deep neural network by inserting a Non-local module into the basic module of the ResNet network. The method can reduce the MAE of the original data from 0.1242 m to 0.0681 m. The research provides technical support for indoor high-precision positioning in the military field. The related results can be applied in the autonomous takeoff and landing of military UAVs, and indoor positioning of military robots.
  • [1] Subedi S, Pyun J. A survey of smartphone-based indoor positioning system using RF-based wireless technologies [J]. Sensors, 2020, 20(24): 7230. doi:  10.3390/s20247230
    [2] Sahinoglu Z, Gezici S, Guvenc I. Ultra-Wideband Positioning Systems: Theoretical Limits, Ranging Algorithms, and Protocols[M]. New York: Cambridge University Press, 2008.
    [3] 文铠. 基于超宽带的室内定位与定向关键技术研究[D]. 武汉: 武汉大学, 2020.

    Wen Kai. Research on the key techniques of ultra-wideband based indoor position and orientation estimation[D]. Wuhan: Wuhan University, 2020. (in Chinese)
    [4] Che F, Ahmed Q, Fontaine J, et al. Feature-based generalized Gaussian distribution method for NLOS detection in ultra-wideband (UWB) indoor positioning system [J]. IEEE Sensors Journal, 2022, 22(19): 18726-18739. doi:  10.1109/JSEN.2022.3198680
    [5] Wu S, Ma Y, Zhang Q, et al. NLOS error mitigation for UWB ranging in dense multipath environments[C]//Proc of IEEE Conference on WCNC, 2007: 1565-1570.
    [6] Venkatesh S, Buehrer R. NLOS mitigation using linear programming in ultrawideband location-aware networks [J]. IEEE Transactions on Vehicular Technology, 2007, 56(5): 3182-3198. doi:  10.1109/TVT.2007.900397
    [7] Yang H, Wang Y, Seow C, et al. UWB sensor-based indoor LOS/NLOS localization with support vector machine learning [J]. IEEE Sensors Journal, 2023, 23(3): 2988-3004. doi:  10.1109/JSEN.2022.3232479
    [8] Nguyen T, Jeong Y, Shin H. Machine learning for wideband localization [J]. IEEE Journal on Selected Areas in Communications, 2015, 33(7): 1357-1380. doi:  10.1109/JSAC.2015.2430191
    [9] Yang X, Zhao F. Echo state network and echo state Gaussian process for non-line-of-sight target tracking [J]. IEEE Systems Journal, 2020, 14(3): 3885-3892. doi:  10.1109/JSYST.2020.2982516
    [10] Bregar K, Mohorcic M. Improving indoor localization using convolutional neural networks on computationally restricted devices [J]. IEEE Access, 2018, 6(1): 17429-17441.
    [11] Angarano S, Mazzia V, Salvetti F, et al. Robust ultra-wideband range error mitigation with deep learning at the edge [J]. Engineering Applications of Artificial Intelligence, 2021, 102: 104278. doi:  10.1016/j.engappai.2021.104278
    [12] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proc of IEEE Conference on CVPR, 2016: 770-778.
    [13] Wang X, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proc of IEEE Conference on CVPR, 2018: 7794-7803.
    [14] Angarano S, Salvetti F, Mazzia V, et al. Deep UWB: A dataset for UWB ranging error mitigation in indoor environments [EB/OL]. [2023-04-10]. https://www.zenodo.org/record/6611037#.ZBGEN3Yz.
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Figures(11)  / Tables(1)

Get Citation
PDF
XML

Article Metrics

Article views(83) PDF downloads(23) Cited by()

Related
Proportional views

Deep learning-based impact mitigation method for UWB NLOS propagation

doi: 10.3788/IRLA20230183
  • 1. College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China
  • 2. Nanhu Laser Laboratory, National University of Defense Technology, Changsha 410073, China
  • 3. College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China
  • Received Date: 2023-04-10
  • Rev Recd Date: 2023-05-10
  • Available Online: 2023-12-22
  • Publish Date: 2023-12-22

Abstract:   Objective  With the continuous development of intelligent technologies and devices, precise positioning technology in the military field is becoming increasingly widespread, and its application scenarios cover both outdoor and indoor environments. Global Navigation Satellite System (GNSS) positioning technology is commonly used for its high positioning accuracy and rich information provision in outdoor environments; However, its positioning accuracy in indoor environments is significantly reduced due to the obstruction of walls and other obstacles. Ultra-Wideband (UWB) technology shows obvious advantages with its high positioning accuracy, firm spatial and temporal resolution, fast transmission rate, and low cost. These advantages make UWB technology particularly suitable for indoor high-precision positioning. In the indoor environment, various obstacles block the propagation channel between the base station and the tag of the UWB system, due to the Non-Line-Of-Sight (NLOS) phenomenon of UWB signals, the positioning accuracy of UWB systems is significantly reduced. Therefore, it is necessary to research the impact mitigation method for UWB NLOS propagation.   Methods  A deep neural network based on deep learning techniques is proposed for UWB NLOS propagation impact mitigation. This deep neural network takes the initial channel impulse response (CIR) of the UWB device as input and the ranging error of the UWB device as output. The experimental analysis shows that the characteristics of CIR data are significantly different under LOS and NLOS propagation conditions (Fig.7), which provides a solid theoretical basis for establishing the mapping relationship between CIR and ranging error using deep learning methods. Meanwhile, the network performance is related to the dimensionality of the input CIR data. The network performance is best when the input CIR data is 128 dimensions (Fig.8). When the input of the deep neural network is 128-dimensional data, too long input will lead to the structural design of the network becoming difficult. And the number of network layers is too small, the network performance can not meet the requirements to achieve good NLOS propagation impact mitigation effect; After the number of network layers increases to a certain degree, the network performance will decrease with the increase of the number of layers. For this reason, the ResNet network is selected in this paper, which enables the gradient to flow effectively to the early layers near the input layer by introducing residual connections in the deep neural network, thus improving the network performance with the increase of layers. At the same time, CIR data, as a time-series signal, correlates its data points. The global features of CIR data must be considered, while local module such as convolution can only extract local features. For this reason, this paper introduces the Non-local module, which can capture the long-distance dependence between locations and extract global information. In summary, the proposed deep neural network is constructed by inserting the Non-local module into the ResNet network's basic module while considering the CIR data's features, and named the deep neural network as NLO-ResNet.   Results and Discussions   In order to evaluate the NLOS propagation impact mitigation performance of the proposed deep neural network, four networks were selected for performance comparison. Four networks include two machine learning-based networks, SVM and MLP, and two deep learning-based networks, CNN and ResNet. Experimental results (Tab.1) show that, due to the increase in the number of layers of the network and the change in the input data, the performance of the deep learning-based network is generally better than that of the machine learning-based network; Among the deep learning-based networks, the CNN network has the worst performance, the ResNet network improves with the increase of the number of layers due to the introduction of residual connections, and the NLO-ResNet network has the best performance, which has the most comprehensive feature extraction of the input CIR data. The mean absolute error (MAE) is reduced by 12.2% compared to the CNN-based network and 4.8% compared to the ResNet-based network, and the learning process of this network converges quickly (Fig.10), and the predicted range error of this network is very close to the actual range error (Fig.11).   Conclusions  To improve the accuracy of UWB systems under NLOS propagation conditions, a deep learning-based NLOS propagation impact mitigation method is proposed, which constitutes a deep neural network by inserting a Non-local module into the basic module of the ResNet network. The method can reduce the MAE of the original data from 0.1242 m to 0.0681 m. The research provides technical support for indoor high-precision positioning in the military field. The related results can be applied in the autonomous takeoff and landing of military UAVs, and indoor positioning of military robots.

    HTML

    0.   引　言

    • 近年来，随着以人工智能、物联网、高性能传感器为代表的智能技术和设备的快速发展，精确定位技术愈发重要。在军事领域，精确定位技术也得到了广泛应用，无论在室内，还是室外环境中，军事领域对精确定位技术都存在强烈的需求。

      全球卫星导航系统（Global Navigation Satellite System, GNSS）定位技术是目前使用最为广泛的室外定位技术，可以提供精确的位置、速度和时间信息。然而，由于墙壁等障碍物的影响，GNSS信号在室内环境中相当微弱，定位精度明显降低，无法满足室内精确定位的需求。此外，室内环境中存在大量障碍物，电磁环境复杂，人员流动密集，以上因素都会导致信号和噪声的变化[1]。在这种情况下，迫切需要研究定位精度更高、鲁棒性更强的室内定位技术。

      在现有的室内定位技术中，超宽带（Ultra-Wideband, UWB）技术近年来受到了广泛的关注。UWB技术不使用传统通信体制，而是通过发送和接收具有纳秒或纳秒级以下的极窄脉冲来传输数据[2]。与Wi-Fi定位技术、射频识别（Radio Frequency Identification, RFID）定位技术、ZigBee定位技术等定位技术相比，UWB技术具有定位精度高、时空分辨率强、传输速率快、成本低等优点，这些优点使得UWB技术特别适合用于室内高精度定位。

      影响UWB技术定位精度的主要因素包括：时钟误差、多路径误差、非视距（Non Line of Sight, NLOS）传播误差、噪声等。其中，对于时钟误差，可通过选择高可靠性的时钟设备或高精度的时钟同步算法等进行抑制；对于多路径误差，可通过时延估计算法进行抑制；在以上影响因素中，NLOS传播误差对UWB技术定位精度的影响最大，一方面是相较于其他室内定位技术，UWB技术定位精度高，NLOS传播带来的误差更加明显，另一方面是UWB技术有效测距范围更远，NLOS传播更加普遍，影响也更加严重[3]。因此，有必要进行UWB NLOS传播影响抑制技术的研究。

      传统的UWB NLOS传播影响抑制技术可分为两个研究方向，分别是NLOS传播识别技术和NLOS传播误差抑制技术。NLOS传播识别技术[4]仅在UWB系统中存在大量节点时可用，应用范围受限；NLOS传播误差抑制技术可通过测距误差估计算法[5]、位置估计算法[6]对误差进行抑制。

      近年来，基于机器学习的UWB NLOS传播影响抑制技术得到了广泛关注。不同于传统方法，该方法不再区分NLOS传播识别和NLOS传播误差抑制两个研究方向，而是在同一框架下实现NLOS传播识别与误差抑制。该方法主要使用UWB信号的接收信号强度（Received Signal Strength Indication, RSSI）、峰度、偏度等波形统计数据作为输入，如基于支持向量机（Support Vector Machine, SVM）[7]、相关向量机（Relevance Vector Machine, RVM）[8]、高斯过程[9]的方法。然而，波形统计数据的采集需要耗费大量人工计算时间，且这些波形统计数据会丢失UWB信号的部分特征，NLOS传播影响抑制效果有限。

      深度学习以复杂神经网络为模型，可以提取大规模数据的多维特征，具有强大的函数近似能力和泛化能力。文献[10]首次使用深度学习中的卷积神经网络（Convolutional Neural Network, CNN）进行UWB NLOS传播影响抑制技术的研究，该方法使用从UWB系统中直接获得的原始信道脉冲响应（Channel Impulse Response, CIR）数据为输入，无需提取UWB信号波形统计数据，避免了浪费大量人工时间。文献[11]使用深度学习和凸优化技术，提出了一种网络模型REMnet，取得了更好的NLOS传播影响抑制效果，同时还证明了其方法在低计算能力设备上运行的有效性。然而，CIR数据作为一种时序信号，以上方法在提取特征的过程中并未考虑其位置之间的长距离依赖性，未捕获输入数据的全局特征。

      为了进一步提升NLOS传播影响抑制效果，在文中，提出了一种基于深度学习的UWB NLOS传播影响抑制方法，该方法通过在残差网络（Residual Network, ResNet）中增加Non-local模块而构建深度神经网络，以从UWB系统中直接获取的CIR数据为输入，测距误差为输出，该深度神经网络可捕获输入数据的全局特征，有效减小NLOS传播对UWB系统精度的影响。

    1.   深度神经网络模型设计

    • UWB设备中的CIR数据有上千个采样点，如此长的CIR数据作为深度神经网络的输入必然会增加网络设计的困难，同时，CIR数据作为一种时序信号，网络设计过程中必须考虑CIR数据采样点位置之间的长距离依赖性，以下重点介绍深度神经网络模型设计的核心思想。

      • 1.1.   深度神经网络基本结构及作用

    • 文中提出的深度神经网络中，用到的基本结构包括：卷积（Convolution, Conv）层、激活函数、批量归一化（Batch Normalization, BN）层、最大汇聚（Maximum Pooling, MaxPool）层、全局平均汇聚（Global Average Pooling, GAP）层。

      Conv层的作用是提取一个局部区域的特征，不同的卷积核相当于不同的特征提取器，与全连接（Fully Connected, FC）层相比，Conv层可以明显减少神经网络参数的数量。

      激活函数的作用是提升深层神经网络对输入的拟合能力。修正线性单元（Rectified Linear Unit, ReLU）函数是近年来使用广泛的激活函数，其主要优点是可以有效防止梯度消失问题，且计算速度快。ReLU函数的表达式如下：

      式中：${\boldsymbol{x}}$为输入向量。

      BN层的作用是对神经网络中任意中间层的数据进行归一化操作，提供有效的数据预处理方法，同时还可以提高网络的泛化能力。BN层的计算表达式如下：

      式中，${{\boldsymbol{x}}^{(l)}}$为第$l$层神经元的输入；$\;\mu $和${\sigma ^2}$为输入的均值和方差；$\varepsilon $为一个非常小的常数；${\boldsymbol{\gamma}} $和${\boldsymbol{\lambda}} $分别代表缩放和平移的参数向量；$ \odot $为矩阵乘法。

      MaxPool层的作用是计算局部区域的最大值，缓解Conv层对位置的过度敏感性；GAP层的作用是进行特征选择，减少参数数量，避免过拟合现象的产生，可视为一种结构化的正则化器。

      • 1.2.   ResNet网络

    • 为了提取输入数据的多维特征，深度神经网络往往需要具有足够多的层数，网络层数越多，参数越多，对输入数据的拟合能力则越强。但是，当深度神经网络的层数增加到一定数量后，网络性能不会上升反而会下降，这种现象使得无法通过单纯增加网络层数来提升网络性能。为了解决这个问题，文献[12]提出了ResNet网络，其核心思想是通过在深度神经网络中引入残差连接，使梯度可以有效地流向靠近输入层的早期层，从而避免网络性能随层数增加而降低。因此，文中借鉴ResNet网络核心思想设计深度神经网络。

      ResNet网络的基本结构是RBU模块，利用多个RBU模块的串联连接可以构建深层神经网络，有效防止梯度消失和梯度爆炸等问题。根据是否包含$1 \times 1$卷积块，RBU模块可分成两类，其基本构成如图1所示，其中$f(x)$是要学习的目标函数。

      Figure 1.  Two categories of RBU modules

      根据所含卷积的次数，RBU模块也可分成两类，18、34层网络的基本模块记为Basicblock，包含2次卷积；50、101、152层网络的基本模块记为Bottleneck，包含3次卷积。相较于Basicblock，Bottleneck将两个$3 \times 3$的Conv层替换为两个$1 \times 1$，一个$3 \times 3$的Conv层，Bottleneck中$3 \times 3$的Conv层首先在一个$1 \times 1$的Conv层下降维，然后在另一个$1 \times 1$的Conv层下做了还原，这样既保持了精度又减少了计算量，两种基本模块的构成如图2所示。常用的ResNet-18网络结构如图3所示。

      Figure 2.  Basicblock (a) and Bottleneck (b)

      Figure 3.  Schematic diagram of ResNet-18 network structure

      • 1.3.   Non-local模块

    • CIR数据是一种时序信号，其采样点位置之间存在长距离依赖性，具有全局特征。对于卷积等local模块，主要考虑的是提取局部区域特征，难以捕获全局特征。

      为了解决local模块存在的问题，文献[13]提出了Non-local模块。该模块可保证输入和输出的尺度不变性，提取全局特征，并直接嵌入任意网络；与local模块相比，该模块只需更少的层数即可达到相同效果，计算效率高。

      Non-local模块的通用计算公式如下：

      式中：$i$和$j$代表的是输入数据的位置索引；$s$为计算输入两点相似度的函数；$h$为计算输入在某个位置特征的函数；$y$为输出；$A$为对输入进行标准化处理的函数。

      Non-local模块计算流程如下：

      形状为$\left[ {N,H,W,C} \right]$的输入${\boldsymbol{x}}$，经过3个$1 \times 1$卷积核得到${\boldsymbol{\theta}} $,${\boldsymbol{\varphi}} $,${\boldsymbol{g}}$, 其形状均为$\left[ {N,H,W,C/2} \right]$；对${\boldsymbol{\theta}} $,${\boldsymbol{\varphi}} $,${\boldsymbol{g}}$, 将$H$, $W$两个维度展开，得到其形状为$\left[ {N,HW,C/2} \right]$；对${\boldsymbol{\varphi }}$进行通道重排，得到其形状为$\left[ {N,C/2,HW} \right]$，随后将其与${\boldsymbol{\theta}} $进行矩阵乘法，得到形状为$\left[ {N,HW,HW} \right]$的矩阵，该矩阵计算的是相似度，随后经Softmax函数进行归一化，得到的矩阵与${\boldsymbol{g}}$进行矩阵乘法，得到形状为$\left[ {N,HW,C/2} \right]$的矩阵，然后将$HW$维度进行伸展，得到其形状为$\left[ {N,H,W,C/2} \right]$；再使用一个$1 \times 1$卷积对通道进行扩展，得到其形状为$\left[ {N,H,W,C} \right]$，与初始输入${\boldsymbol{x}}$的形状一致，最后，将该矩阵与输入${\boldsymbol{x}}$相加，得到最终输出${\boldsymbol{z}}$，该计算流程如图4所示。

      Figure 4.  Non-local module calculation flow chart

      • 1.4.   NLO-ResNet网络

    • 将Non-local模块插入ResNet网络的基本结构RBU模块中，并参考ResNet网络中模块的排列方式，即可构建文中提出的深度神经网络，并将其命名为NLO-ResNet，其基本模块NLRBU如图5所示，根据是否包含$1 \times 1$卷积块，将其分别命名为NLRBU-Iden和NLRBU-Conv。

      Figure 5.  Two basic types of modules for NLO-ResNet: NLRBU-Iden (a) and NLRBU-Conv (b)

      NLO-ResNet网络可通过增加基本模块的数量来提升网络性能，但当网络层数增加到一定数量后，网络性能提升不再明显，且由于参数的增加，网络训练时间会显著增加。文中通过多次实验，并考虑训练时间和网络性能之间的平衡，所使用的NLO-ResNet网络共有22层，其网络结构如图6所示。

      Figure 6.  Schematic diagram of NLO-ResNet network structure

    2.   CIR数据分析与数据集构成

      2.1.   CIR数据分析

    • 如图7所示，UWB信号在LOS和NLOS传播条件下的CIR数据存在明显的区别。在LOS传播条件下，CIR数据中环境噪声分量较小，即使存在多径分量也能清晰地分辨出直接路径信号。在NLOS传播条件下，CIR信号存在多个较高峰值，难以分辨直接路径信号。

      Figure 7.  Typical schematic of CIR data under LOS and NLOS propagation conditions

      CIR数据在传播条件、障碍物材料等条件不同的情况下均存在不同的特点，这为采用深度学习方法提取CIR数据特征、建立CIR数据与测距误差之间的映射关系提供了坚实的理论基础。

      存储在UWB芯片中的CIR数据共有1016个采样点，其中的冗余采样点不仅对网络性能没有贡献，所含噪声还会产生负面作用。为了减少深度神经网络的参数数量，提高网络的计算速度，可以在保证网络性能的前提下，减少CIR数据的输入维度。

      文献[10]已经证明CIR数据中的152个采样点即可体现关于传播条件的大部分特征；文中在输入CIR数据为1~152维的范围内进行了实验，实验结果如图8所示，当输入CIR数据低于8维时，无法得到有效的NLOS传播影响抑制效果，在输入CIR数据为8~128维的范围内，网络性能随输入维度的增加而提升，在128~152维的范围内，网络性能随输入维度的增加而降低。因此，文中以下讨论均基于输入CIR数据包含128个采样点。

      Figure 8.  Schematic of the variation of the network performance with the dimensionality of the input CIR data

      • 2.2.   数据集构成

    • 文中在DeepUWB[14]公共数据集上进行了实验，以证明所提出的深度神经网络的有效性。该数据集获取过程如下：装有UWB标签的载体在充满障碍物的环境中沿固定路径运动，使用Decawave EVB1000设备获得UWB测距信息，使用徕卡AT403激光跟踪仪获得真实距离信息，在获得足够数量的样本后，通过修改基站的位置或障碍物的类型和位置来改变配置。该数据集对室内常见障碍物造成的NLOS传播条件进行了模拟，采集样本数量多，测量结果精确，应用场景丰富，适合用于方法验证。

      该数据集中每个数据包含5项内容，分别为 CIR数据、测距误差、房间类型、障碍物类型、UWB测量距离。其中，房间类型包括：一个$10 \;{\rm{ m}} \times 5 \;{\rm{ m}}$的大房间，一个$5\;{\rm{ m}} \times 5 \;{\rm{ m}}$的中等房间，一个$5 \;{\rm{ m}} \times 3.5 \;{\rm{ m}}$的小房间；障碍物类型包括10种，分别为墙壁、苯板、塑料、胶合板、纸箱、液晶电视、金属板、木门、玻璃板、金属窗。文中使用大房间（共18422个样本）和小房间（共17601个样本）的数据为训练集，中等房间（共13210个样本）的数据为测试集。

    3.   实验和结果分析

      3.1.   基线和评价指标

    • 为了更好地评价所提出的深度神经网络的NLOS传播影响抑制性能，文中选取了其他几种网络进行性能比较，选取的网络分别是SVM、多层感知机（Multi-Layer Perceptron, MLP）、CNN、ResNet。

      其中，SVM和MLP是传统的基于机器学习的网络，这两种网络的输入均采用6个人工提取的波形统计特征：RSSI、第一路径RSS值、平均超额延迟、均方根延迟扩展、峰度和偏度。对于SVM，将其核函数设置为径向基函数；对于MLP，将其设置为3层结构，其中，输入层共6个神经元，隐藏层共128个神经元，输出层共1个神经元。

      CNN、ResNet和NLO-ResNet均为基于深度学习的网络。CNN、ResNet、NLO-ResNet这3种网络的结构相同，主要区别是组成网络的基本模块不同，3种网络的基本模块对比见图9。相较于CNN，ResNet增加了残差连接，NLO-ResNet增加了残差连接和Non-local模块。

      Figure 9.  Comparison of the basic modules of CNN (a), ResNet (b), and NLO-ResNet (c)

      为了评估模型在数据集上的性能，引入了平均绝对误差(Mean Absolute Error, MAE)，其定义如下：

      式中：$\hat {\boldsymbol{m}} = \left\{ {{{\hat m}_1},{{\hat m}_2}, \cdots ,{{\hat m}_n}} \right\}$为预测值；${\boldsymbol{m}} = \left\{ {{m_1},{m_2}, \cdots ,{m_n}} \right\}$为真实值；$n$为样本数量。

      • 3.2.   超参数设置

    • 通过重复、多次实验，并衡量准确性和效率的重要性，最终确定文中的超参数设置如下：优化算法选择Adam算法，其动量参数设置为：$\;{\beta _1} = 0.9$、${\;\beta _2} = 0.999$、$\varepsilon = {10^{ - 8}}$；学习率设置为learning rate=$3 e - 4$，批量大小设置为batch size=32，损失函数设置为MAE，迭代次数设置为epoch=50。

      该深度神经网络通过Pytorch框架实现，服务器的配置为：32 GB RAM、GeForce RTX 3090 GPU。

      • 3.3.   实验结果分析

    • 实验结果如表1所示，SVM和MLP等传统的基于机器学习的网络，虽计算时间短，但性能较差。基于深度学习的网络普遍性能更优，原因是其网络层数更多、泛化能力更强。相较于SVM和MLP， CNN网络的性能提升不明显；ResNet网络的性能明显，其MAE可达0.0715 m，相较于CNN网络降低了近7.9%；在所有网络中，NLO-ResNet网络性能最优，其MAE可达0.0681 m，相较于CNN网络下降了近12.2%，相较于ResNet网络下降了近4.8%。

      NetworkMAE/m
      Raw data0.1242
      SVM0.0782
      MLP0.0815
      CNN0.0776
      ResNet0.0715
      NLO-ResNet0.0681

      Table 1.  Experiment results of network performance comparison

      训练过程中，NLO-ResNet网络在测试集上的损失函数变化曲线如图10所示。可以看到，其学习过程快速收敛。

      Figure 10.  Variation of the loss function on the test sets

      NLO-ResNet网络在测试集上输出的预测测距误差和数据集记录的实际测距误差的对比如图11所示。从图中可以看出，在大多数情况下，预测测距误差与实际测距误差非常接近。原数据集中由于设备等因素的影响，出现了个别异常值，这些异常值影响了网络性能，未来的研究工作可以首先对数据集的数据进行平滑处理，剔除异常值，进一步提升网络性能。

      Figure 11.  Comparison chart of predicted range error and actual range error

      综上，文中提出的基于NLO-ResNet网络的UWB NLOS传播影响抑制方法的主要优势如下：与基于机器学习的方法相比，该方法无需对输入数据进行额外处理，节省了人工提取UWB信号波形统计特征的时间，且网络性能更好；与文献[10]提出的基于CNN的方法，文献[11]提出的基于REMnet的方法相比，该方法考虑了CIR数据的时序特征，可以捕获CIR数据位置之间的长距离依赖性，提取CIR数据的全局特征，网络性能进一步提升。

    4.   结　论

    • 为了提高UWB系统在NLOS传播条件下的定位精度，提出了一种基于深度学习的NLOS传播影响抑制方法。该方法通过在ResNet网络中插入Non-local模块而构建深度神经网络NLO-ResNet，该网络直接以UWB系统的CIR数据为输入，无需对数据进行额外处理，大量实验证明，与现有其他网络相比，该网络的NLOS传播影响抑制效果最优，可将原始数据的测距平均绝对误差从0.1242 m降低至0.0681 m。相关研究为军事领域的室内高精度定位提供了技术支撑，相关成果可以在军事领域得到应用。

Reference (14)

Catalog

    版权所有 © 2019 《红外与激光工程》编辑部｜ Address: 58 Zhonghuan West Road, Tianjin Airport Economic Zone｜ Post Code: 300308

    津ICP备19007885号-1

    Supported by: Beijing Renhe Information Technology Co. Ltd  

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return