Inertial Odometry Using Hybrid Neural Network with Temporal Attention for Pedestrian Localization

Yingying Wang1; Hu Cheng1; Max Q.-H. Meng2

2022

10.1109/TIM.2022.3186704

IEEE Transactions on Instrumentation and Measurement   Impact Factor & Quartile

1557-9662

1557-9662

In this work, a novel hybrid neural network with temporal attention (HNNTA) is proposed for inertial pedestrian localization. The HNNTA model employs the convolutional neural network (CNN) for extracting sectional features from the IMU data, followed by the long short-term memory (LSTM) network to capture the global temporal information. A temporal attention mechanism is designed to weigh the hidden states produced by the LSTM network and generate the final features for velocity prediction. Specifically, the proposed temporal attention mechanism is composed of the CNN feature refinement module and the sigmoid score normalization function. We utilize different 1-D filters to refine the temporal hidden states from previous refined time indexes and form the value matrix with each row containing different features along with the entire window time indexes and each column representing individual features from the same time spans. We then employ the sigmoid function to normalize the dot-product alignment between features from different time spans and that of the last refined time index. We employ the RoNIN dataset to evaluate the HNNTA model, which contains the largest and most natural IMU measurements. We employ extensive erosion experiments to show the effectiveness of the HNNTA model design. Compared with the state-of-the-art method, the HNNTA model provides 10.39% higher 50th percentile accuracy for all phone carriers that have been seen in the training set and 8.69% higher for those that have not been seen. The real-world experiments with IMU measurements collected on the CUHK campus further demonstrate the better generalization capability of the HNNTA model.

Pedestrian dead reckoning inertial measurement unit (IMU) sensor calibration inertial state estimation velocity measurement indoor localization

SCI ; EI

English

Others

National Key Research and Development Program of China[2019YFB1312400] ; Hong Kong Research Grants Council (RGC) Collaborative Research Fund (CRF)[C4063-18G]

Engineering ; Instruments & Instrumentation

Engineering, Electrical & Electronic ; Instruments & Instrumentation

WOS:000838427900007

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

ENGINEERING

Web of Science

1.Robotics, Perception and Artificial Intelligence Lab in the Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
2.Shenzhen Key Laboratory of Robotics Perception and Intelligence, and the Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China

Yingying Wang,Hu Cheng,Max Q.-H. Meng. Inertial Odometry Using Hybrid Neural Network with Temporal Attention for Pedestrian Localization[J]. IEEE Transactions on Instrumentation and Measurement,2022,PP(99):1-1.

Yingying Wang,Hu Cheng,&Max Q.-H. Meng.(2022).Inertial Odometry Using Hybrid Neural Network with Temporal Attention for Pedestrian Localization.IEEE Transactions on Instrumentation and Measurement,PP(99),1-1.

Yingying Wang,et al."Inertial Odometry Using Hybrid Neural Network with Temporal Attention for Pedestrian Localization".IEEE Transactions on Instrumentation and Measurement PP.99(2022):1-1.