Imitation Learning for Variable Speed Contact Motion for Operation up to Control Bandwidth

Robots have several requirements, including environmental adaptability, to operate in the real-world environment. Moreover, the desired success rate for task completion must be achieved. In this regard, end-to-end learning for autonomous operation is currently being investigated. However, the issue of the operating speed has not been investigated in detail. Therefore, in this study, we propose a method for generating variable operating speeds while adapting to perturbations in the environment. When the work speed changes, a nonlinear relationship occurs between the operating speed and force (e.g., inertial and frictional forces). However, the proposed method can be adapted to nonlinearities by utilizing a small amount of motion data. We experimentally evaluated the proposed method by erasing a line using an eraser fixed to the tip of the robot. Furthermore, the proposed method enables a robot to perform a task faster than a human operator and is capable of operating at the control bandwidth.