Imitation learning for variable speed motion generation over multiple actions

TL;DR

This paper presents a neural network-based imitation learning approach for generating variable speed robotic motions across multiple actions, effectively controlling task completion times while considering physical forces.

Contribution

It introduces a method to learn multiple actions with variable speeds using neural networks, improving over previous simple reciprocating motion models.

Findings

The proposed model accurately reproduces specified task completion times.

It effectively handles multiple actions and joints in motion generation.

The method considers physical phenomena like inertia and friction.

Abstract

Robotic motion generation methods using machine learning have been studied in recent years. Bilateral control-based imitation learning can imitate human motions using force information. By means of this method, variable speed motion generation that considers physical phenomena such as the inertial force and friction can be achieved. However, the previous study only focused on a simple reciprocating motion. To learn the complex relationship between the force and speed more accurately, it is necessary to learn multiple actions using many joints. In this paper, we propose a variable speed motion generation method for multiple motions. We considered four types of neural network models for the motion generation and determined the best model for multiple motions at variable speeds. Subsequently, we used the best model to evaluate the reproducibility of the task completion time for the input completion time command. The results revealed that the proposed method could change the task completion time according to the specified completion time command in multiple motions.