电子测量与仪器学报

廖亚桢,刘昱,张立强,李虎,宫霄霖.面向 PDR 定位系统的多层感知机 IMU 阵列数据融合方法[J].电子测量与仪器学报,2022,36(8):35-42

面向 PDR 定位系统的多层感知机 IMU 阵列数据融合方法

Multi-layer sensor IMU array data fusion method for PDR positioning system

DOI：

英文关键词:inertial measurement unit array pedestrian dead reckoning multi-layer perceptron data fusion

基金项目:国家自然科学基金（61771338）项目资助

作者	单位
廖亚桢	1.天津大学微电子学院
刘昱	1.天津大学微电子学院
张立强	1.天津大学微电子学院
李虎	1.天津大学微电子学院
宫霄霖	1.天津大学微电子学院

Author	Institution
Liao Yazhen	1.School of Microelectronics, Tianjin University
Liu Yu	1.School of Microelectronics, Tianjin University
Zhang Liqiang	1.School of Microelectronics, Tianjin University
Li Hu	1.School of Microelectronics, Tianjin University
Gong Xiaolin	1.School of Microelectronics, Tianjin University

摘要点击次数: 515

全文下载次数: 780

中文摘要:

为提高低成本惯性测量单元(intertial measurement unit,IMU)阵列的行人航位推算(pedestrian dead reckoning,PDR)定位精度,首次提出了采用多层感知机(multi-layer perceptron,MLP)实现低成本 IMU 阵列数据融合的算法,通过将自主设计的 IMU 阵列和高精度 IMU 同步运动来获得 IMU 阵列的测量数据(包括三轴加速度和三轴角速度)和高精度 IMU 的测量数据,以高精度 IMU 的测量数据作为标签,利用 MLP 将 IMU 阵列的测量数据融合,预测出物体的实际加速度和角速度,并用定位算法进行验证。在定位实验中,使用 MLP 融合后的预测数据的 PDR 定位精度比使用单个 IMU 测量数据的 PDR 定位精度提高了 33. 9%;比使用简单平均处理的 IMU 阵列测量数据的 PDR 定位精度提高了 20. 8%;比使用最小二乘法融合的 IMU 阵列测量数据的 PDR 定位精度提高了 11. 6%,证明了本文所提出方法的可行性和有效性。

英文摘要:

In order to improve the positioning accuracy of pedestrian dead reckoning ( PDR) for low-cost inertial measurement unit (IMU) arrays, this paper proposes for the first time the use of multi-layer perceptron (MLP) to achieve algorithms for low-cost IMU array data fusion. The measurement data of the IMU array ( including triaxial acceleration and triaxial angular velocity) and the measurement data of the high-precision IMU are obtained by synchronizing the motion of the self-designed IMU array and the highprecision IMU, and the measurement data of the high-precision IMU is used as a label. The MLP fuses the measurement data of the IMU array, predicts the actual acceleration and angular velocity of the object, and uses the positioning algorithm to verify it. In the localization experiment, the PDR localization accuracy using the prediction data fused by MLP is 33. 9% higher than the PDR localization accuracy using a single IMU measurement data; it is 20. 8% higher than the PDR localization accuracy using the simple average processing IMU array measurement data; it is 11. 6% higher than the PDR localization accuracy using the IMU array measurement data fused by the least square method, which proves the feasibility and effectiveness of the method proposed in this paper.

查看全文查看/发表评论下载PDF阅读器