モータ関節角と電流値を用いた再帰型神経回路モデルによるペグ挿入動作生成

抄録

In this research, we propose a motion generation method for inserting rod-shaped pegs from the neighborhood of the hole by using only the joint angles and current values measured from the robot arm’s motors. Conventionally, expensive torque sensors are used about peg-in-hole. However, we confirmed that the peg inserting motion can be generated by learning a neural network using not torque sensors but the motor angles and current values. The learning model is a recursive neural Network integrated and learned by time series data composed of joint angles and current values made with a remote teaching system and it predicts the next motion at a certain time by its position and variance. We confirmed that flexible peg insertion can be realized from multiple initial positions by feedback control with proposed method using motor's joint angles and current values at each time after learning.