Grinding motion generation based on human motion by variational autoencoder

2021 ◽  
Vol 2021 (0) ◽  
pp. 1A1-E17
Author(s):  
Keito SUGAWARA ◽  
Masahiro AITA ◽  
Toshiaki TSUJI
Keyword(s):  
Human Motion ◽  
Motion Generation ◽  
Variational Autoencoder

Sensorimotor Control for Human Motion Generation—A Review

2012 ◽  
Vol 1 (2) ◽  
pp. 161-179 ◽  
Author(s):  
Chen-Hui Hu ◽  
Qin-Huai Zhang ◽  
Wen-Chieh Lin
Keyword(s):  
Sensorimotor Control ◽  
Human Motion ◽  
Motion Generation

A Robot Arm Motion Generation Based on Learning of Objects Shape and Human Motion

2018 ◽  
Vol 2018 (0) ◽  
pp. 2A1-F14
Author(s):  
Sho TAJIMA ◽  
Tokuo TSUJI ◽  
Yosuke SUZUKI ◽  
Tetsuyou WATANABE ◽  
Kenichi MOROOKA ◽  
...  
Keyword(s):  
Human Motion ◽  
Robot Arm ◽  
Motion Generation ◽  
Arm Motion

scholarly journals Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions

2020 ◽  
Vol 34 (07) ◽  
pp. 12281-12288
Author(s):  
Zhenyi Wang ◽  
Ping Yu ◽  
Yang Zhao ◽  
Ruiyi Zhang ◽  
Yufan Zhou ◽  
...  
Keyword(s):  
Human Action ◽  
Human Motion ◽  
Motion Generation ◽  
Action Sequence ◽  
Sequence Generation ◽  
Latent Space ◽  
Action Sequences ◽  
Mixed Classes ◽  
Standard Action ◽  
Net Framework

Human-motion generation is a long-standing challenging task due to the requirement of accurately modeling complex and diverse dynamic patterns. Most existing methods adopt sequence models such as RNN to directly model transitions in the original action space. Due to high dimensionality and potential noise, such modeling of action transitions is particularly challenging. In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality. Conditioned on a latent sequence, actions are generated by a frame-wise decoder shared by all latent action-poses. Specifically, an implicit RNN is defined to model smooth latent sequences, whose randomness (diversity) is controlled by noise from the input. Different from standard action-prediction methods, our model can generate action sequences from pure noise without any conditional action poses. Remarkably, it can also generate unseen actions from mixed classes during training. Our model is learned with a bi-directional generative-adversarial-net framework, which can not only generate diverse action sequences of a particular class or mix classes, but also learns to classify action sequences within the same model. Experimental results show the superiority of our method in both diverse action-sequence generation and classification, relative to existing methods.

scholarly journals A Recurrent Variational Autoencoder for Human Motion Synthesis

2017 ◽  
Author(s):  
Ikhsanul Habibie ◽  
Daniel Holden ◽  
Jonathan Schwarz ◽  
Joe Yearsley ◽  
Taku Komura
Keyword(s):  
Human Motion ◽  
Motion Synthesis ◽  
Variational Autoencoder ◽  
Human Motion Synthesis

scholarly journals Graph-based Normalizing Flow for Human Motion Generation and Reconstruction

2021 ◽  
Author(s):  
Wenjie Yin ◽  
Hang Yin ◽  
Danica Kragic ◽  
Marten Bjorkman
Keyword(s):  
Human Motion ◽  
Motion Generation

A script engine for realistic human motion generation

2010 ◽  
Vol 38 (1/2/3) ◽  
pp. 55
Author(s):  
Jun Xiao ◽  
Tong qiang Guo
Keyword(s):  
Human Motion ◽  
Motion Generation
Sign in / Sign up

Export Citation Format

Share Document