Humatronics (1) - natural interaction between human and networked robot using human motion recognition

The 6th International Conference on Soft Computing and Intelligent Systems, and the 13th International Symposium on Advanced In

Zhen

et al. 2012

In this paper, the authors are target to construct an assistant system that is applying the ideal of user model with robots and Smartphone for supporting elderly people. The human data can reflect a person's life style, thus the authors collect human's daily life information as the basis to construct the user model, and apply the user model to offer appropriate services to users. We collect the human data by 3D acceleration sensor, and apply the user model for the system to provide service to user appropriately. Because the user models are able to filter and class the user data, thus we choose to apply the user model for the system. We collect human motions by using 3D acceleration sensors that are carried by users, and save these data into database for using in creating Motion logs. Life logs can then be created from Motion logs. The user models create by mining Life logs. The system can then provide direct assistant to elderly people by applying the user models. The service the system provides is showing the social information of these people, who have the same interesting, to encourage elderly people talk to each other. The research shows the possibility of applying the user models and supporting elderly people with their social situation.

Section: A the Service For Elderly Peoplementioning

confidence: 99%

Section: B the Service For Helper Or Familymentioning

confidence: 99%

A elderly people assistant system applying user model with robots and Smartphone

The 6th International Conference on Soft Computing and Intelligent Systems, and the 13th International Symposium on Advanced In

Zhen

et al. 2012

“…Moreover, we also develop a function for Home log that is to allow user view the rate of using electric equipment of Home log directly. We applied the pointing movement system, which is development by Sato-Shimokawara et al [10] as the basis of our function. The original system designed for using pointing to indicate the robot's moving direction.…”

Section: Applicationmentioning

confidence: 99%

Data Mining of Life Log for Developing a User model-based Service Application

2012 IEEE International Conference on Automation Science and Engineering (CASE)

Yamaguchi

2012

In this research, the authors aimed to mining Life logs for developing a user model-based service application. Life logs can be constructed by analyzing Motion logs, which are obtained from questionnaires, or motion data collected from sensors. And the user models, which help applications to provide appropriate service, can be constructed by mining these Life logs.To achieve the above goal, first we collect Motion logs. Although Motion logs can be easily obtained from the questionnaires, it is more complicate to extract necessary information from the raw data gathered from sensors. Therefore, we adopted the fuzzy inference and fuzzy membership functions to obtain Motion logs from the raw data of the sensors. Life logs can then be created from Motion logs. Finally, we construct different user models by mining Life logs to support applications providing appropriate service. We also introduce several related applications in this paper.Our research results show the great potential of applying user models-based approach to service applications. By adopting our approach, the services ability and scope of applications in service grid can be further enhanced and expanded.

“…The application is to detect hand's pointing movements, recognize the user's instruction from hand motions, and adapt to environment information to provide personal services. Our work based on Pointing movement system [1], which is developed by Yamaguchi laboratory, to interact with a robot. This system recognizes a user's pointing movement with following steps: a stereo camera capture user's hand motion, the indicated point is calculated from the captured image, the system recognize the user's instruction from indicated point and the situation (environmental information), and then, control a robot motion.…”

Section: Introductionmentioning

confidence: 99%

Application to Pointing Movement System for Human-Robot Interface using Foreground Segmentation with Gaussian Mixture Model

Yamashita

Biomedical Engineering / 817: Robotics Applications

et al. 2014

Human-robot interface has become one of main research areas on robotic systems. The authors propose an application to Pointing movement system for humanrobot interface, and focuses on developing an intuitive operation using a new manner. Our application utilized a stereo camera to capture human's images, and utilize them as primary sources of information retrieval. We apply Foreground segmentation with Gaussian Mixture Model (GMM) for fingertip recognition to be the main image processing method to propose system. The system is mainly executed in the following steps: a stereo camera captures the user's hand motion, the system recognizes the user's instruction from the hand motion and the situation (as well as environmental information), and then, control a robot motion. In this paper, we describe our applied image processing method, which employs foreground segmentation with GMM for fingertip recognition, and overall concepts of the proposed application is then also defined. We present a robot demonstration to specify proposed system. Finally, the demonstration experiment is presented to show the effectiveness and research potential of our application.