Idioma:

Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles

Milam, Gary ; Xie, Baijun ; Liu, Runnan ; Zhu, Xiaoheng ; Park, Juyoun ; Kim, Gonwoo ; Park, Chung Hyuk

Sensors (Basel, Switzerland), 2022-10, Vol.22 (20), p.7701 [Periódico revisado por pares]

Basel: MDPI AG

Texto completo disponível

Citações Citado por

Enviar para

Título:
Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles
Autor: Milam, Gary ; Xie, Baijun ; Liu, Runnan ; Zhu, Xiaoheng ; Park, Juyoun ; Kim, Gonwoo ; Park, Chung Hyuk
Assuntos: Accelerometers ; Algorithms ; autonomous ground vehicle ; Computational linguistics ; Cost function ; Dead reckoning ; Extended Kalman filter ; Global positioning systems ; GPS ; Gravity ; inertial navigation system ; Inertial platforms ; Language processing ; Localization ; mobile robot ; Natural language interfaces ; Neural networks ; Noise ; Noise measurement ; Online instruction ; Optical radar ; Optimal control ; Performance evaluation ; Quaternions ; Remote sensing ; Robot control ; Robots ; Sensors ; Simultaneous localization and mapping ; Transportation systems ; Unmanned ground vehicles ; Velocity
É parte de: Sensors (Basel, Switzerland), 2022-10, Vol.22 (20), p.7701
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
These authors contributed equally to this work.
Descrição: Extended Kalman filter (EKF) is one of the most widely used Bayesian estimation methods in the optimal control area. Recent works on mobile robot control and transportation systems have applied various EKF methods, especially for localization. However, it is difficult to obtain adequate and reliable process-noise and measurement-noise models due to the complex and dynamic surrounding environments and sensor uncertainty. Generally, the default noise values of the sensors are provided by the manufacturer, but the values may frequently change depending on the environment. Thus, this paper mainly focuses on designing a highly accurate trainable EKF-based localization framework using inertial measurement units (IMUs) for the autonomous ground vehicle (AGV) with dead reckoning, with the goal of fusing it with a laser imaging, detection, and ranging (LiDAR) sensor-based simultaneous localization and mapping (SLAM) estimation for enhancing the performance. Convolution neural networks (CNNs), backward propagation algorithms, and gradient descent methods are implemented in the system to optimize the parameters in our framework. Furthermore, we develop a unique cost function for training the models to improve EKF accuracy. The proposed work is general and applicable to diverse IMU-aided robot localization models.
Editor: Basel: MDPI AG
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles

Milam, Gary ; Xie, Baijun ; Liu, Runnan ; Zhu, Xiaoheng ; Park, Juyoun ; Kim, Gonwoo ; Park, Chung Hyuk

Basel: MDPI AG

Buscando em bases de dados remotas. Favor aguardar.