An Autonomous Home Care Mobile Robot for Visual Monitor and Navigation System

碩士 === 國立臺灣科技大學 === 自動化及控制研究所 === 100 === The research area of mobile robots has grabbed lots of research interests in recent years and has successfully demonstrated many concepts for solve people’s daily problems such as clean robots, entertainment robots, and the most industrial robots. Home care...

Full description

Bibliographic Details
Main Authors: Po-Han Lu, 呂柏翰
Other Authors: Min-Fan Lee
Format: Others
Language:en_US
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/2d4x2s
Description
Summary:碩士 === 國立臺灣科技大學 === 自動化及控制研究所 === 100 === The research area of mobile robots has grabbed lots of research interests in recent years and has successfully demonstrated many concepts for solve people’s daily problems such as clean robots, entertainment robots, and the most industrial robots. Home care system has been proposed by some countries with finite medical resources to provide better cares especially to elderly and disabled people. However, the key technologies of an autonomous home care mobile robot are still developing to deal with different situations. This thesis proposed an autonomous home care mobile robot including three parts such as visual monitor, mapping and localization, and path planning on a mobile robot. First, a visual monitor is used to detect abnormal motions of the elderly or disabled person living alone when an emergency occurs. Once an abnormal motion is detected, it triggers the second system, mapping and localization to build up a map of the unknown environment and estimates further environmental parameters such as target position, obstacle positions, and the mobile robot position. After that, an improved Rapidly-exploring Random Tree (RRT) is used to generate an optimal path to help the mobile robot reach the target for providing necessary sensing information to the remote medical center for further assistances. This thesis shows the accuracy of the visual monitor is about 80% for abnormal motion detection and successfully estimates through mapping and localization. Finally, an improved RRT is used to generate a collision-free path to quickly guide the mobile robot to the target position with 64% reduced computation.