Open AccessImprovement of Performance of Navigation System for Supporting Independence Rehabilitation of Wheelchair - Bed Transfer
Author(s) -
Jin Kato,
Genbu Deguchi,
Jun Inoue,
Masami Iwase
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1487/1/012041
Subject(s) - wheelchair , kalman filter , estimator , position (finance) , computer science , kinematics , simulation , extended kalman filter , navigation system , estimation , computer vision , control theory (sociology) , artificial intelligence , control engineering , engineering , control (management) , mathematics , statistics , physics , systems engineering , finance , classical mechanics , world wide web , economics
The purpose of this research is to improve the position and angle estimation accuracy of the wheelchair guide system for Hemiplegic patients. The wheelchair guide system aims to assist the patients to transfer between their wheelchair and bed. This system prompts properly to user depending on the situation as same as care worker. Therefore, the system is developed to prompt the measured position and angle of wheelchair. The position estimator uses an AR marker to detect the wheelchair position. However, its estimation is contaminated by measurement noises and sometimes fails because the marker is out of the camera’s field of view. To improve the estimation of position and moving direction, we introduce the kinematic model of the wheelchair and utilize the Extended Kalman Filter with the model. In this paper, we describe the self-position estimation method of the navigation system and AR marker, with the estimation method using Kalman Filter.