Kaoru Mitsuhashi

The curved surface visualization of the expert behavior for skill transfer using Microsoft Kinect

Method of teaching and inheriting for skill is almost oral. It is not quantitative but qualitative. Quantitative inheriting of skill is difficult. In this paper, after tracking of a subjects skill motion using Microsoft Kinect, a subjects motion is visualized as the curved surface. A curved surface is fitted in the positions of a subjects joint, or the direction of trajectories. Expert and beginner perform swimming and karate motion. After the motions are tracked, the trajectories of joints are transformed to a curved surface. The difference of an action between an expert and a beginner is extracted by investigating curvatures and form on the visualized curved surface. Therefore, we expected that technical skill is transferred easily.

Miniaturization and drive evaluation of modular robot by 3D printer

The modular robot is constructed by the same shape and function module. The robot can transform and exchange, because it is multiple modules and function. In previous paper, we manufactured the module by 3D printer, and evaluated the mechanical function of the simple module and modular robot. In this paper, the module is miniaturized and joint parts are improved. Joint parts are used tenon joint in place of ball joint. Additionally, we confirmed the validity of the driving modular robot by comparing the previous.

Suggestion of Motion Velocity/Acceleration Curved Surface.

The skill teaching/succession method is not quantitative but qualitative, which is abstract oral or gesture expression. Quantitative teaching is difficult for teacher/instructor. In previous research, Expert and beginner perform the sports and entertainment motion, and the character of the motion curved surface is analysed using Microsoft Kinect (RGBD camera). The character is the maximum curvature and surface area. However, the usage of characters is uncertain. In this research, we investigate the correlation of maximum curvature and surface area from motion curved surface in before and after training. Therefore, we visualize the different correlation of experts and beginners from the characters and the transition of the skill training.

Skill Level Evaluation of Motion Curved Surface Character

The skill teaching/succession method is not quantitative but qualitative, which is abstract oral or gesture expression. Quantitative teaching is difficult for teacher/instructor. In previous research, Expert and beginner perform the sports and entertainment motion, and the character of the motion curved surface is analysed using Microsoft Kinect (RGBD camera). The character is the maximum curvature and surface area. However, the usage of characters is uncertain. In this research, we investigate the correlation of maximum curvature and surface area from motion curved surface in before and after training. Therefore, we visualize the different correlation of experts and beginners from the characters and the transition of the skill training.

Functional Evaluation of the Solid Model Creation using 3D Direct Drawing System

3D model of computer is usually created using 3D CAD software, but 3D direct drawing method is still developing the research. In this paper, we suggest and construct the 3D direct drawing system with ARToolKit and develop the required creating methods and tools. The method is the creating solid algorithm using projective methods. The algorithm is the converting multiple surfaces into a solid. After that, the functionality of the methods and tools are evaluated using the Taguchi method (quality engineering). In addition, we investigate the optimal condition of the creating methods and tools required for modeling.

Educational system of physical motion based on 3D biomechanism evaluation

This paper presents an educational support system of physical motion with body motion based on three-dimensional biomechanism evaluation. The difficult point of the physical motion with body motion is that human cannot attain the perfect copy or imitation of the reference skill motion because each skeleton size, functions and numbers of motor of human are different, we call it the imperfect imitation problem. The proposed system uses a human motion capture which observes and records the movement of human in real time, and extract a 3D (three dimensional) skeleton model from the observed movement data. So, our system is to support the judgment of the expert instructors. In our experiment to evaluate the effectiveness of the proposed system, some education of sports, such as crawl motion in swimming, darts throw motion, Karate defend motion are adopted. And, we certainly will show the useful results.

Education system of skill succession based on 3D evaluation and improvement in time series

This paper presents an educational support system of skill succession with body motion based on 3D (three-dimensional) biomechanics evaluation. Skill succession using body motion seems different because human cannot attain the perfect copy or imitation of the reference skill motion. We call it the imperfect imitation problem. Then, we propose the 3D skeleton motion viewer and e-learning education system. The learner cannot move the expert motion, however, watching only 3D skeleton motion movie. So, our system supports learner using the judgment of the expert instructors (teacher). In experiment, to evaluate the effectiveness of the proposed system, some education of sports such as swimming, darts game and karate are adopted. The evaluation is a learners improvement and teachers satisfaction from the interview.

Suggestion of creating solid method using projective method in 3D real space with microsoft kinect

3D model is normally designed by 3D-CAD software or animation software, but a 3D direct drawing method is still a developing research. In a previous study, we suggest a 3D direct drawing method for polygonal/curved surface model using Microsoft Kinect. In this study, some subjects performe the gesture expressing a solid, analyzed the gesture trajectory. And we construct the creating solid algorithm using projective methods from the results. The algorithm is the converting multiple surfaces into a solid. After that, the subjects are performed gesture expressing again and the creating model is measured. Because of the validity confirmation of our algorithm.

Reduced DoFs of digital hand based on anatomy for real time operation

This paper describes a model of using a digital hand, which mimics human hands, operates dynamically in real time operation. Focusing on real time operation, we consider a model structure of digital hand with reduced DoFs (degree of freedoms) as an approximated model, where the reduction is based on the anatomical and medical hand analysis. There some problems because of the approximated model. To overcome the problems, some techniques are implemented into the model. We examine how the model is able to mimic the movement of human hands.

A STRUCTURE AND SOFT FINGER MODEL OF DIGITAL HAND FOR REAL-TIME DEXTEROUS MANIPULATION

This paper describes a structure and soft finger model of digital hand for real-time dexterous manipulation. From investigations of human dexterous manipulation by using high speed camera, the structure and skin conditions of digital hand are defined. To evaluate our model, bar spinning as dexterous manipulation is adopted. Comparing manipulations with human hand and digital hand, we discuss its effectiveness and problems of our model.