.png){kind=icon}
返回
Optimizing Neural Network as Locomotion Controller With Motion Data
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2834380.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes a novel method of optimizing locomotion controller for virtual characters, which is constructed with the deep neural network and learned with the assistance of existing motion data. The learning is accomplished with a progressive reward function by starting from a simple reward function and gradually imposing advanced requirements on the gait pattern. A multi-critic model is proposed to address the dynamically changing reward function by evaluating the individual goal in a separate fashion. This strategy proves effective in avoiding the local minima that are likely to occur when a set of weighted reward functions are introduced at the beginning of the optimization. The results show that the integration of motion data not only ensures the consistency between the synthetic and original motions but also accelerates the learning of network parameters. We demonstrate the application of our method to a variety of virtual characters (cheetah, hopper, 2-D walker, and 3-D humanoid) performing various tasks (walking, running, jumping, and traversing at different velocities and across uneven terrains).
Keyword:
Character animation
deep neural network
motion capture data
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Lobster shal: comparison with Drosophila shal and native potassium currents in identified neuronsOAAI
OAAI分享收藏Interaction of iodoacetamidofluorescein‐labelled tropomyosin with deoxyribonuclease I.png)
FEBS Letters
FEBS LettersIF0
PREAI
分享收藏分享收藏
查看更多内容