An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications

TL;DR

This paper introduces a hierarchical imitation learning framework with independently trainable layers for long-term task execution, demonstrating improved success rates and significantly reduced training time.

Contribution

The paper presents a novel hierarchical model with independent training of layers for long-term imitation learning tasks, enabling reuse and efficiency.

Findings

Achieved success rates comparable or higher than hierarchical RNNs.

Reduced training time to less than 1/20 of conventional methods.

Successfully executed unlearned tasks by reusing trained lower layers.

Abstract

Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains challenging. Therefore, a novel framework for imitation learning is proposed to solve this problem. The proposed framework comprises upper and lower layers, where the upper layer model, whose timescale is long, and lower layer model, whose timescale is short, can be independently trained. In this model, the upper layer learns long-term task planning, and the lower layer learns motion primitives. The proposed method was experimentally compared to hierarchical RNN-based methods to validate its effectiveness. Consequently, the proposed method showed a success rate equal to or greater than that of conventional methods. In addition, the proposed method required less than 1/20 of the training time compared to conventional methods. Moreover, it succeeded in executing unlearned tasks by reusing the trained lower layer.