Indoor person position estimation system based on integration of multiple information
Naoki Uzawa, Taku KUDOU, Jun Miura, Shuji Oishi · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2018
Estimation of person position is important for a service robot in a wide indoor environment. In this research, we aim to develop a person position estimation system based on integrating multiple information, signal data and position estimation result by a mobile robot. The system consists of a server that manages data, mobile robots, and mobile devices. The information acquired by the robot and the mobile device is sent to the server, and estimates the position of each person based on the collected data. Wi-Fi location estimation uses Gaussian process and particle filter. The position estimation by the mobile robot is obtained based on the robot localization result and the position of the person measured by the robot.