RNN-Aided Human Velocity Estimation from a Single IMU
RNN-Aided Human Velocity Estimation from a Single IMU
复制标题
DOI：
10.3390/s20133656
复制
发表时间：
2020-07-01
期刊：
影响因子：
3.9
通讯作者：
Mutschler, Christopher
中科院分区：
文献类型：
--
作者：
Feigl, Tobias;Kram, Sebastian;Mutschler, Christopher
行人航位推算（PDR）使用惯性测量单元（imu），结合速度和方向估计来确定位置。速度的估计仍然具有挑战性，因为在很长一段时间内，有噪声的加速度和角速度信号的集成会导致很大的漂移。经典的方法来估计速度优化特定的应用，传感器的位置，和类型的运动，需要广泛的参数调整。我们的新型混合滤波器将卷积神经网络（CNN）和双向循环神经网络（BLSTM）（从传感器信号中提取空间特征并跟踪它们的时间关系）与线性卡尔曼滤波器（LKF）结合在一起，提高了速度估计。我们的实验表明，即使在高度动态的情况下，对不同的运动状态和方向变化的鲁棒性。我们将新架构与传统、机器和深度学习方法进行了比较，并表明从单个未校准的IMU来看，我们的新架构在速度方面优于最先进的技术(
Pedestrian Dead Reckoning (PDR) uses inertial measurement units (IMUs) and combines velocity and orientation estimates to determine a position. The estimation of the velocity is still challenging, as the integration of noisy acceleration and angular speed signals over a long period of time causes large drifts. Classic approaches to estimate the velocity optimize for specific applications, sensor positions, and types of movement and require extensive parameter tuning. Our novel hybrid filter combines a convolutional neural network (CNN) and a bidirectional recurrent neural network (BLSTM) (that extract spatial features from the sensor signals and track their temporal relationships) with a linear Kalman filter (LKF) that improves the velocity estimates. Our experiments show the robustness against different movement states and changes in orientation, even in highly dynamic situations. We compare the new architecture with conventional, machine, and deep learning methods and show that from a single non-calibrated IMU, our novel architecture outperforms the state-of-the-art in terms of velocity (