End-to-end Manipulator Calligraphy Planning via Variational Imitation Learning

TL;DR

This paper introduces a novel deep imitation learning approach for robotic Japanese calligraphy, utilizing a 3D trajectory and pen orientation, effectively handling complex artistic expressions and overcoming distribution shift issues.

Contribution

It presents a new neural network combining variational auto-encoder, bi-directional LSTM, and MLP for 3D calligraphy planning from demonstrations.

Findings

Successful real-world robot calligraphy execution

Effective handling of distribution shift in imitation learning

Source code and dataset will be publicly available

Abstract

Planning from demonstrations has shown promising results with the advances of deep neural networks. One of the most popular real-world applications is automated handwriting using a robotic manipulator. Classically it is simplified as a two-dimension problem. This representation is suitable for elementary drawings, but it is not sufficient for Japanese calligraphy or complex work of art where the orientation of a pen is part of the user expression. In this study, we focus on automated planning of Japanese calligraphy using a three-dimension representation of the trajectory as well as the rotation of the pen tip, and propose a novel deep imitation learning neural network that learns from expert demonstrations through a combination of images and pose data. The network consists of a combination of variational auto-encoder, bi-directional LSTM, and Multi-Layer Perceptron (MLP). Experiments are conducted in a progressive way, and results demonstrate that the proposed approach is successful in completion of tasks for real-world robots, overcoming the distribution shift problem in imitation learning. The source code and dataset will be public.