电子测量与仪器学报

邸克,刘茄鑫,杜佳佳,任杰,赵卫峰,刘宇.关于 PDR 算法步长估计模型的改进研究[J].电子测量与仪器学报,2022,36(11):178-185

关于 PDR 算法步长估计模型的改进研究

Research on the improvement of step size estimation model of PDR algorithm

DOI：

英文关键词:pedestrian positioning step estimation Kalman filter BP neural network

基金项目:国家自然科学基金委员会面上项目(52175531)、国家自然科学基金委员会青年科学基金项目(11704053)资助

作者	单位
邸克	1.重庆邮电大学光电工程学院
刘茄鑫	1.重庆邮电大学光电工程学院
杜佳佳	1.重庆邮电大学光电工程学院
任杰	1.重庆邮电大学光电工程学院
赵卫峰	1.重庆邮电大学光电工程学院
刘宇	1.重庆邮电大学光电工程学院

Author	Institution
Di Ke	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications
Liu Jiaxin	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications
Du Jiajia	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications
Ren Jie	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications
Zhao Weifeng	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications
Liu Yu	1.School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications

摘要点击次数: 1390

全文下载次数: 1282

中文摘要:

为了更加精确地判别基于微惯性测量单元( IMU)的行人定位信息,本文深入研究了传统行人航迹推算(PDR)算法模型,发现传统算法所采用的判别条件单一且精准度不高。针对传统算法中步长估计模型不准确的问题,本研究首先提出一种基于扩展卡尔曼滤波的误差补偿优化算法,以实现 IMU 内集成的加速度计、陀螺仪等传感器的误差补偿。将优化后的原始数据放入 BP 神经网络算法对单参数步长估算经验模型进行训练。实验结果表明,基于 BP 神经网络融合基础模型的步长算法相比单纯的基础步长模型,闭环精度提高了 0. 3%以上,开环误差减小了 8. 5 倍,基于 BP 神经网络的改进 PDR 算法可以有效抑制惯性算法的误差发散。

英文摘要:

In order to better distinguish the pedestrian positioning information based on micro inertial measurement unit ( IMU), this paper deeply studies the traditional pedestrian dead reckoning (PDR) algorithm model, and finds that the traditional algorithm has single discrimination conditions, low accuracy and is not suitable for scenes with a variety of terrain. Aiming at the problem of inaccurate step estimation model in traditional algorithms, this study first proposes an error compensation optimization algorithm based on extended Kalman filter (EKF) to realize the error compensation of accelerometer, gyroscope and other sensors integrated in IMU. The study put the optimized original data into BP neural network algorithm to train the single parameter step estimation empirical model. The experimental results show that the step size algorithm based on BP neural network fusion basic model can improve the closed-loop accuracy by more than 0. 3% and reduce the open-loop error by 8. 5 times compared with the simple basic step size model. The improved PDR algorithm based on BP neural network can effectively suppress the error dispersion of inertial algorithm.

查看全文查看/发表评论下载PDF阅读器