Generative Adversarial Nets in Robotic Chinese Calligraphy

Fei Chao, Jitu Lv, Dajun Zhou, Longzhi Yang, Chih-Min Lin, Changjing Shang, Changle Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

30 Citations (Scopus)
149 Downloads (Pure)

Abstract

Conventional approaches of robotic writing of Chinese character strokes often suffer from limited font generation methods, and thus the writing results often lack of diversity. This has seriously restricted the high quality writing ability of robots. This paper proposes a generative adversarial nets-based calligraphic robotic framework, which enables a robot to learn writing fundamental Chinese strokes with rich diversity and good originality. In particular, the framework considers the learning process of robotic writing as an adversarial procedure which is implemented by three interactive modules including a stroke generation module, a stroke discriminative module and a training module. Noting that the stroke generative module included in the conventional generative adversarial nets cannot solve the non-differentiable problem, the policy gradient commonly used in reinforcement learning is thus adapted in this work to train the generative module by regarding the outputs from the discriminative module as rewards. Experimental results demonstrate that the proposed framework allows a calligraphic robot to successfully write fundamental Chinese strokes with good quality in various styles. The experiment also suggests the proposed approach can achieve human-level stroke writing quality without the requirement of a performance evaluation system. This approach therefore significantly boosts the robotic autonomous creation ability.
Original languageEnglish
Title of host publicationICRA 2018
Subtitle of host publicationIEEE International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages1104-1110
Number of pages7
ISBN (Electronic)9781538630815
ISBN (Print)9781538630822
DOIs
Publication statusPublished - 13 Sept 2018

Publication series

NameICRA
PublisherIEEE
ISSN (Electronic)2577-087X

Keywords

  • Writing
  • Trajectory
  • Training
  • Gallium nitride
  • Manipulators
  • Probability distribution

Fingerprint

Dive into the research topics of 'Generative Adversarial Nets in Robotic Chinese Calligraphy'. Together they form a unique fingerprint.

Cite this