Autonomous animation of humanoid robots

A humanoid robot can actuate its multiple degrees of freedom to form whole body motions that convey meanings in different input signals. This thesis investigates how to autonomously animate a real humanoid robot given an input signal, such as gesturing to speech or dancing to the emotion expressed i...

全面介紹

Saved in:
書目詳細資料
主要作者: Tay, Junyun
其他作者: Veloso, Manuela
格式: Theses and Dissertations
語言:English
出版: 2016
主題:
在線閱讀:https://hdl.handle.net/10356/69279
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Nanyang Technological University
語言: English
id sg-ntu-dr.10356-69279
record_format dspace
spelling sg-ntu-dr.10356-692792023-03-04T16:33:04Z Autonomous animation of humanoid robots Tay, Junyun Veloso, Manuela Chen I-Ming School of Mechanical and Aerospace Engineering Carnegie Mellon University Robotics Research Centre DRNTU::Engineering::Mechanical engineering::Robots A humanoid robot can actuate its multiple degrees of freedom to form whole body motions that convey meanings in different input signals. This thesis investigates how to autonomously animate a real humanoid robot given an input signal, such as gesturing to speech or dancing to the emotion expressed in music. This thesis addresses five core challenges: Representation of motions, Mappings of motions to meanings where meanings are represented as labels, Selection of relevant motions that considers the similarity between labels and audience preferences, Synchronization of motions to the input signal to form motion sequences, and Stability of the motion sequences (RMS^3). This thesis introduces a complete algorithm that solves the challenges of RMS^3, and selects a motion sequence to animate using a weighted criteria of audience preferences and stability. The approach and algorithms in this thesis are general to autonomously animate humanoid robots, and this thesis uses the NAO humanoid robot to autonomously animate speech and music. DOCTOR OF PHILOSOPHY (MAE) 2016-12-12T02:50:55Z 2016-12-12T02:50:55Z 2016 Thesis Tay, J. (2016). Autonomous animation of humanoid robots. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/69279 10.32657/10356/69279 en 173 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Mechanical engineering::Robots
spellingShingle DRNTU::Engineering::Mechanical engineering::Robots
Tay, Junyun
Autonomous animation of humanoid robots
description A humanoid robot can actuate its multiple degrees of freedom to form whole body motions that convey meanings in different input signals. This thesis investigates how to autonomously animate a real humanoid robot given an input signal, such as gesturing to speech or dancing to the emotion expressed in music. This thesis addresses five core challenges: Representation of motions, Mappings of motions to meanings where meanings are represented as labels, Selection of relevant motions that considers the similarity between labels and audience preferences, Synchronization of motions to the input signal to form motion sequences, and Stability of the motion sequences (RMS^3). This thesis introduces a complete algorithm that solves the challenges of RMS^3, and selects a motion sequence to animate using a weighted criteria of audience preferences and stability. The approach and algorithms in this thesis are general to autonomously animate humanoid robots, and this thesis uses the NAO humanoid robot to autonomously animate speech and music.
author2 Veloso, Manuela
author_facet Veloso, Manuela
Tay, Junyun
format Theses and Dissertations
author Tay, Junyun
author_sort Tay, Junyun
title Autonomous animation of humanoid robots
title_short Autonomous animation of humanoid robots
title_full Autonomous animation of humanoid robots
title_fullStr Autonomous animation of humanoid robots
title_full_unstemmed Autonomous animation of humanoid robots
title_sort autonomous animation of humanoid robots
publishDate 2016
url https://hdl.handle.net/10356/69279
_version_ 1759854465377107968