Imitation Learning with Additional Constraints on Motion Style using Parametric Bias

TL;DR

This paper introduces a method that enhances imitation learning by incorporating parametric bias, allowing robots to adapt their motion styles according to specified constraints, improving task performance in untrained environments.

Contribution

It proposes adding parametric bias to imitation learning networks to control motion style constraints, enabling more adaptable robotic motion reproduction.

Findings

Robots can modify motion styles as intended using the proposed method.

The method effectively constrains joint velocity, muscle length velocity, and muscle tension.

Experiments demonstrate successful adaptation on PR2 and MusashiLarm robots.

Abstract

Imitation learning is one of the methods for reproducing human demonstration adaptively in robots. So far, it has been found that generalization ability of the imitation learning enables the robots to perform tasks adaptably in untrained environments. However, motion styles such as motion trajectory and the amount of force applied depend largely on the dataset of human demonstration, and settle down to an average motion style. In this study, we propose a method that adds parametric bias to the conventional imitation learning network and can add constraints to the motion style. By experiments using PR2 and the musculoskeletal humanoid MusashiLarm, we show that it is possible to perform tasks by changing its motion style as intended with constraints on joint velocity, muscle length velocity, and muscle tension.