Design and experiment of centimeter UWB ranging error correction model based on BP neural network
-
摘要: 在室内复杂环境下，超宽带(UWB)测距误差难以通过常规方法进行有效补偿，严重制约了其定位精度. 在分析室内环境下UWB测距误差分布特点的基础上，设计了两种不同结构的BP神经网络误差改正模型. 模型BP1输入单个标签与4个基站的测距值，输出对应的4个测距误差；模型BP2输入一对标签、基站的三维坐标，输出对应的一个测距误差. 以高精度全站仪测量结果作为参考值，对网络进行训练，并对模型改正前后的测距和定位精度进行了对比分析. 结果表明：两种模型均能有效改正测距误差，提升定位精度.其中BP1测距和定位精度分别提高83.0%、75.9%，BP2测距和定位精度平均提高91.7%、93.8%. BP2相比于BP1能够更加有效地提高测距和定位精度，使定位精度由dm级提升至cm级.Abstract: In complex indoor environment, ultra wide band (UWB) ranging error can not be effectively compensated by conventional methods, which seriously restricts its positioning accuracy. Based on the analysis of the distribution characteristics of UWB ranging error in indoor environment, two different BP network error correction models with different structures are designed. Model BP1 inputs the ranging values of a single label and four base stations, and outputs four corresponding ranging errors; Model BP2 inputs the three-dimensional coordinates of a pair of labels and a base station, and outputs one corresponding ranging error. The network is trained with high precision total station measurement result as reference value, and the ranging and positioning accuracy before and after model correction are compared and analyzed. The results show that both models can effectively correct ranging errors and improve positioning accuracy. BP1 ranging and positioning accuracy are improved by 83.0%, 75.9%, and BP2 ranging and positioning accuracy is improved by 91.7%, 93.8% on average. BP2 can improve the ranging and positioning accuracy more effectively than BP1, and the positioning accuracy can be improved from decimeter level to centimeter level.
-
表 1 长时间测距点上测距误差统计
基站 距离/m 均值/cm 标准差
/cmRMSE/cm 标准差/均值 /% B1 5.18 21.54 1.18 21.57 5.5 B2 7.51 27.12 0.78 27.13 2.9 B3 7.54 19.21 1.48 19.26 7.7 B4 5.27 20.73 1.61 20.79 7.8 
下载: 导出CSV
表 2 测距误差统计
cm 基站 均值 RMSE 最大值 最小值 B1 22.2 23.8 52.2 3.2 B2 26.2 27.5 46.7 6.3 B3 30.4 31.3 55.8 3.5 B4 24.5 25.8 51.9 7.3 全部 25.8 27.2 55.8 3.2
下载: 导出CSV
-
[1] KIM N S, RABAEY J M. A 3.1-10.6-GHz 57-bands CMOS frequency synthesizer for UWB-based cognitive radios[J]. IEEE transactions on microwave theory and techniques, 2018, 66(9): 4134-4146. DOI: 10.1109/TMTT.2018.2852283 [2] 郭少彬, 沈锋, 杨莹. 基于UWB的室内协同定位方法[J]. 电子信息对抗技术, 2018, 33(4): 6-10,75. DOI: 10.3969/j.issn.1674-2230.2018.04.002 [3] 李荣冰, 王念曾, 刘建业, 等. 面向相对导航的UWB测距误差估计与补偿方法[J]. 仪器仪表学报, 2019, 40(5): 28-35. [4] 王川阳, 王坚, 余航, 等. 测距误差改正的超宽带定位系统研究[J]. 测绘科学, 2019, 44(1): 98-103, 117. [5] 盛坤鹏, 王坚. 超宽带NLOS测距误差改正模型[J]. 北京测绘, 2020, 34(2): 250-254. [6] WEN K, YU K G, LI Y B, et al. An experimental correction model for UWB through-the-wall distance measurements[C]//IEEE International Conference on Ubiquitous Wireless Broadband, 2016. DOI: 10.1109/ICUWB.2016.7790570 [7] 牟大中, 王明飞, 曹鹏, 等. 基于小波神经网络的超宽带测距优化方法研究[J]. 北京印刷学院学报, 2018, 26(12): 85-89. DOI: 10.3969/j.issn.1004-8626.2018.12.022 [8] WYMEERSCH H, MARANO S, GIFFORD W M, et al. A machine learning approach to ranging error mitigation for UWB localization[J]. IEEE transactions on communications, 2012, 60(6): 1719-1728. DOI: 10.1109/TCOMM.2012.042712.110035 [9] YIN Z D, CUI K, WU Z L, et al. Entropy-based TOA emation and SVM-based ranging error mitigation in UWB ranging systems[J]. Sensors, 2015, 15(5): 11701-11724. DOI: 10.3390/s150511701 [10] FONTAINE J, RIDOLFI M, HERBRUGGEN B V, et al. Edge inference for UWB ranging error correction using autoencoders[J]. IEEE access, 2020(8): 139143-139155. DOI: 10.1109/ACCESS.2020.3012822 [11] 刘培原, 王坚, 盛坤鹏, 等. 非视距误差神经网络改正的超宽带定位模型研究[J]. 导航定位与授时, 2020, 7(3): 93-104. [12] 徐爱功, 刘韬, 隋心, 等. UWB/INS紧组合的室内定位定姿方法[J]. 导航定位学报, 2017, 5(2): 14-19. DOI: 10.3969/j.issn.2095-4999.2017.02.003 [13] 仪玉杰, 黄智刚, 苏雨. 一种UWB与PDR融合的行人室内定位方法[J]. 导航定位学报, 2019, 7(3): 38-43, 50. DOI: 10.3969/j.issn.2095-4999.2019.03.007 [14] LIU F, LI X, WANG J, et al. An adaptive UWB/MEMS-IMU complementary Kalman filter for indoor location in NLOS environment[J]. Remote sensing, 2019, 11(22): 2628. DOI: 10.3390/rs11222628 [15] 武汉大学测绘学院测量平差学科组. 误差理论与测量平差基础[M]. 武汉: 武汉大学出版社, 2014. [16] CHAN Y T, HO K C. A simple and efficient estimator for hyperbolic location[J]. IEEE transactions on signal processing, 1994, 42(8): 1905-1915. DOI: 10.1109/78.301830 -
点击查看大图
图(10) / 表(5)
计量
- 文章访问数: 597
- HTML全文浏览量: 209
- PDF下载量: 59
- 被引次数: 0
