An Image-Based Imitation Learning Framework for Robotic Writing Tasks | IEEE Conference Publication | IEEE Xplore

An Image-Based Imitation Learning Framework for Robotic Writing Tasks


Abstract:

Robotic writing, particularly in the realm of traditional Chinese calligraphy, poses unique challenges due to the intricate nature of stroke patterns and the high precisi...Show More

Abstract:

Robotic writing, particularly in the realm of traditional Chinese calligraphy, poses unique challenges due to the intricate nature of stroke patterns and the high precision required. This paper presents an innovative image-based imitation learning framework designed to address these challenges by enabling robots to acquire and generalize writing skills from static images. By transforming static images into dynamic formats and incorporating a novel deviation analysis method, the framework enhances the learning of stroke thickness and allows for skill generalization across different writing scenarios. The proposed framework’s effectiveness is demonstrated through extensive simulations and real-world experiments.
Date of Conference: 03-05 October 2024
Date Added to IEEE Xplore: 12 November 2024
ISBN Information:

ISSN Information:

Conference Location: Leeds, United Kingdom

References

References is not available for this document.