Pose-Invariant Inertial Odometry for Pedestrian Localization
Pose-Invariant Inertial Odometry for Pedestrian Localization
复制标题
用于行人定位的姿态不变惯性里程计
DOI：
10.1109/tim.2021.3093922
复制
发表时间：
2021
影响因子：
5.6
通讯作者：
M. Meng
中科院分区：
文献类型：
--
作者：
Yingying Wang;Hu Cheng;Chaoqun Wang;M. Meng
智能手机中的惯性传感器可以在没有全球定位系统（GPS）信号或信标的情况下进行行人定位的相对状态测量。任何这样的导航方法都应该注意到这样一个现实，即手机被放置在与人体有关的不受控制的各种姿势上。在这项工作中，我们专注于从原始惯性测量单元（IMU）测量中估计行人的位置，而不受设备携带方式的约束，并提出了一种新的深度惯性里程计解决方案。通过提出连续旋转的表达式，我们可以摆脱对传感器应用程序接口（API）提供的不可靠方向的依赖。此外，我们提出了一种新的损失公式，将速度表示为平均速度大小和移动方向。通过公共RoNIN数据集对所提出的方法进行了评估。然后通过在中大校园的真实场景试验来评估公共数据集训练的网络模型的定位性能。实验结果表明，我们的模型能够提供稳健的速度估计，并产生比最先进的惯性里程计方法更准确的轨迹。具体而言，香港中文大学校园的定位评估包含60分钟的惯性信号，长度为3公里。所训练的里程计网络的第30百分位精度为2.26 m，第50百分位精度为4.98 m。
Inertial sensors in smartphones enable the relative state measurements for pedestrian localization without global positioning system (GPS) signals or beacons. Any such navigation method should notice the reality that the phone is placed at uncontrolled variant poses with respect to the human body. In this work, we focus on pedestrian position estimation from the raw inertial measurement unit (IMU) measurements without any constraint on the device carrying manners and propose a novel deep inertial odometry solution. By presenting the expression of continuous rotating, we are able to release the reliance on the unreliable orientation provided by the sensor application program interface (API). Moreover, we propose a novel loss formulation by representing the velocity as the average velocity magnitude and the moving direction. The proposed approach was assessed via the public RoNIN dataset. The localization performance of the public dataset trained network model was then evaluated by real scenario trials in the CUHK campus. Experimental results show that our model is capable of providing robust velocity estimates and generating more accurate trajectories than state-of-the-art inertial odometry methods. Specifically, the localization evaluation in the CUHK campus contains 60-min inertial signals with a length of 3 km. The trained odometry network is with the 30th percentile accuracy of 2.26 m and the 50th percentile accuracy of 4.98 m.