The document describes an attendant robot system for elderly users that uses a ZigBee 3D acceleration sensor network and Kinect sensor for user recognition. The system includes a mobility robot mounted with a ZigBee access point to detect a unique ID tag carried by the user. It also uses a Kinect sensor to detect users in front of the robot. The robot is able to navigate to and interact with the recognized user based on information from the sensor network and Kinect sensor. The authors developed this proposed system and performed an experiment to test it.
The document describes an attendant robot system for elderly users that uses a ZigBee 3D acceleration sensor network and Kinect sensor for user recognition. The system includes a mobility robot mounted with a ZigBee access point to detect a unique ID tag carried by the user. It also uses a Kinect sensor to detect users in front of the robot. The robot is able to navigate to and interact with the recognized user based on information from the sensor network and Kinect sensor. The authors developed this proposed system and performed an experiment to test it.
The document describes an attendant robot system for elderly users that uses a ZigBee 3D acceleration sensor network and Kinect sensor for user recognition. The system includes a mobility robot mounted with a ZigBee access point to detect a unique ID tag carried by the user. It also uses a Kinect sensor to detect users in front of the robot. The robot is able to navigate to and interact with the recognized user based on information from the sensor network and Kinect sensor. The authors developed this proposed system and performed an experiment to test it.
Tetsuya Kaneko Faculty of System Design Tokyo Metropolitan University Tokyo, Japan kaneko-tetsuya@sd.tmu.ac.jp Kouhei Tanaka Faculty of System Design Tokyo Metropolitan University Tokyo, Japan tanaka-kouhei@sd.tmu.ac.jp Ho Yihsin Faculty of System Design Tokyo Metropolitan University Tokyo, Japan ho-yihsin@sd.tmu.ac.jp Yasunari Fujimoto Faculty of System Design Tokyo Metropolitan University Tokyo, Japan yfujimoto@sd.tmu.ac.jp Toru Yamaguchi Faculty of System Design Tokyo Metropolitan University Tokyo, Japan yamachan@tmu.ac.jp
Abstract The authors developed an Attendant Robot system for the elderly. The robot system is used to prevent user from being at a loss. The system uses ZigBee-3D acceleration sensor and Kinect sensor. Attendant Robot mounts the ZigBee access point, and the ZigBee accelerometer tag is attached to users. The ZigBee access point knows that user comes near to Attendant Robot by finding the tag. This tag has a unique ID, so Attendant Robot reacts to correlative ID only. Kinect sensor detects people who stand in front of the Attendant Robot. This system recognizes user by using function of Kinect and ZigBee sensor. Attendant Robot navigates user using this system. In this paper, the authors set up the proposed system and performed experiment. Keywordsuser recognition, Attendant Robot, ZigBee sensor network, elderly service I. INTRODUCTION Recently, various interaction robots are created and work in many places. Mobility robots are also created for various ways. For example, Nagao et al. [1] developed multi direction smooth at narrow passage, and Kawagishi et al. [2] developed a table type robot which supports users in standing and walking. Therefore we thought that collaboration with interaction robot and mobility robot enables robot to interact with user adapting to user and environment. This paper proposes mobility Attendant Robot with 3D accelerometer sensor network and Kinect sensor. In previous research, the authors developed a navigation system which combined interaction robot and mobility robot together [3]. In this paper, in addition to navigation, we also added recognition system which uses ZigBee-3D acceleration sensor and Kinect sensor into the proposed Attendant Robot. The ZigBee-3D acceleration sensor and access point have a unique ID. The user recognition system recognizes a user, who is the nearest to the mobility robot, using this unique identify number. Similarly, the user area recognition system recognizes an area where user is. Kinect sensor recognizes humans skeleton and gesture. It also measures the distance from user to the mobility robot. The following sections explain the mobility Attendant Robot system in more detail. Section 2 shows system outline. Section 3 explains the robots navigation flowchart. Section 4 explains user recognition systems using 3D accelerometer and Kinect sensor. Section 5 shows the experimental results. And section 6 is conclusions. II. SYSTEM OUTLINE This section describes the outline of mobility Attendant Robot. We had developed mobility function and an interaction function for the Attendant Robot. A user is asked to put ZigBee accelerometer tag in his/her pocket. ZigBee access point is mounted on mobility function, and connects with tags. The system measures distance from user to Attendant Robot by field intensity. Attendant Robot moves to user's desired destination using mobility function and interacts with user by its utterance and gesture functions using interaction function. The proposed Attendant Robot is shown in Figure 1. It has three sensors; laser range finder (LRF), Kinect, and ZigBee sensor. LRF is used for collision avoidance. Kinect is able to detect human, but cannot recognize whether detected human is the user or not. Therefore, the authors use ZigBee sensor for user recognition. With these three sensors, if interaction part or mobility part needs different functions, the proposed robot is able to change interaction part or mobility part based on the situation. For example, if the user is unsteadiness in walking, mobility robot changes to SVT- 001 developed by Vector Inc. Because it has handrail, user is able to hang on to Attendant Robot. PDF created with pdfFactory trial version www.pdffactory.com