慣性センサによる手首推定位置に基づいたロボット遠隔教示システムの構築

抄録

Japanese society is rapidly aging, and its birthrate is low, leading to a reduction of the working population. Therefore, industrial robots are increasingly expected to serve as substitutes for human beings. Conventional teaching methods with robots include remote teaching and direct teaching. These teaching methods have problems in terms of difficulty teaching sensibly and teacher safety. In order to solve these problems, sensuous but remote teaching is ideal for the teacher. In this research, We propose a remote and sensuous teaching system by inertial sensors. We extracted the target position and posture information of the robot to be taught using inertial sensors and applied our system to the actual robot. In this paper, We attach one inertial sensor to trapezius, upper arm and forearm to estimate the trajectory of the wrist. And the 6 DoF robot arm remote teaching system was built. To verify the effectiveness of this system, wrist estimation position accuracy verification experiment, trajectory following experiment, position control experiment, and comparison experiment with other teaching device have conducted. As a result, the effectiveness of remote teaching system by inertial sensors was shown.