Kuroda Yoji
   Department   Undergraduate School  , School of Science and Technology
   Position   Professor
Language English
Publication Date 2021/03
Type Academic Journal
Peer Review Peer reviewed
Title EKF-based self-attitude estimation with DNN learning landscape information
Contribution Type Co-authored (other than first author)
Journal Robomech Journal
Journal TypeAnother Country
Publisher Springer
Volume, Issue, Page 8(9)
Authorship Last author,Corresponding author
Author and coauthor Ryota Ozaki, Yoji KURODA
Details This paper presents an EKF-based self-attitude estimation with a DNN (deep neural network) learning landscape information. The method integrates gyroscopic angular velocity and DNN inference in the EKF. The DNN predicts a gravity vector in a camera frameThis paper presents an EKF-based self-attitude estimation with a DNN (deep neural network) learning landscape information. The method integrates gyroscopic angular velocity and DNN inference in the EKF. The DNN predicts a gravity vector in a camera frame.
URL for researchmap https://robomechjournal.springeropen.com/articles/10.1186/s40648-021-00196-3