Understanding the Behavior of Data-Driven Inertial Odometry With Kinematics-Mimicking Deep Neural Network

Understanding the Behavior of Data-Driven Inertial Odometry With Kinematics-Mimicking Deep Neural Network

In navigation, deep learning for inertial odometry (IO) has recently been investigated using data from a low-cost IMU only. The measurement of noise, bias, and some errors from which IO suffers is estimated with a deep neural network (DNN) to achieve more accurate pose estimation. While numerous stu...

Full description

Bibliographic Details
Main Authors: Quentin Arnaud Dugne-Hennequin, Hideaki Uchiyama, Joao Paulo Silva Do Monte Lima
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Inertial odometry
dead reckoning
deep neural network
kinematics
navigation
IMU
Online Access:https://ieeexplore.ieee.org/document/9366470/

Internet

https://ieeexplore.ieee.org/document/9366470/

Similar Items