Host: The Japan Society of Mechanical Engineers
Name : [in Japanese]
Date : May 10, 2017 - May 13, 2017
In Japan, low birthrate and aging is progressing rapidly. We need to compensate for the labor shortage, because the working population reduces. As a solution to this problem, the introduction of a robot can be considered. Conventional teaching methods include remote teaching and direct teaching. These teaching methods have problems in terms of difficulty teaching sensibly and safety of the teacher. We extracted the target position / posture of the robot to be taught using motion sensors and verified by simulation before applying the actual machine. As a result, we also found that the accuracy of estimation of trajectory is improved largely by adding some angles to the initial estimated posture along z-axis of which initial posture is estimated by geomagnetic sensor. As a result of the simulation, we found that the hand trajectory estimated from the motion sensor can be applied as the tip trajectory of the manipulator.
