Motion recognition using 3D accelerometer sensor network for Mobility Assistant Robot

Abstract

The authors proposed a 3D Accelerometer Sensor Network for Mobility Assistant Robot. The Mobility Assistant Robot is composed of a Mobility Robot, a Smart Robot and ZigBee Accelerometers. The Mobility robot is used to assist walking and standing up. It serves as both table and walker so user can take both advantages. The Smart Robot communicates with user by their gestures and utterances. A ZigBee accelerometer is attached on user's waist to record user's conditions such as room position, posture, walking, getting up, and falling down. The experimental results showed the proposal method recognizes user's falling down with 98.4% recognition rate. With 3D accelerometer, the Mobility Assistant Robot identifies the person who is the nearest and quickly informs the user's falling down conditions.

Estimation of Basic Activities of Daily Living Using ZigBee 3D Accelerometer Sensor Network

“…Each access point has approximately twenty meters radio range. In the previous research, the authors developed motion recognition algorithms for this sensor network [5]. With these algorithms, this sensor recognizes user's position, posture, walking conditions, falling down conditions and getting up conditions.…”

“…Because, our activities are not only with sounds, and we do not always have my mobile phone in a house. In previous research, we succeeded to recognize 7 motions; lying, sitting, standing, walking, running, getting up, and falling down, using only one 3D acceleration sensor [5]. This paper focuses location.…”

Developing a Robotic Service System by Applying a User Model-Based Application for Supporting Daily Life

“…We applied the motion detection method proposed by Ishiguro et al [1]. As with their method, we applied a fuzzy inference method as the motion recognition algorithm and a fuzzy membership function into the system for recognizing motion.…”

“…A sensor on a user's body collects coordination data and sends the data to a receiving device. Then, using the fuzzy inference and fuzzy membership functions for the motion recognition [1], we can obtain motion logs from the motion data. Actimarker calculates the amount of exercise as metabolic equivalents (METs) per minute, which represents the intensity of physical activity and depends on body weight and exercise time to calculate the amount of calories burned.…”

“…We collected life logs from motion data, which was directly obtained from sensors carried by users. Because motion data cannot be directly applied, we use fuzzy inference and fuzzy membership functions to analyse the original motion data so as to obtain motion logs [1]. Motion logs can help obtain life logs, which can be mining to construct user models.…”