Knowledge Commons of Institute of Automation,CAS
Motor-Cortex-Like Recurrent Neural Network and Multi-Tasks Learning for the Control of Musculoskeletal Systems | |
Jiahao Chen1,2,3; Hong Qiao1,2,3 | |
发表期刊 | IEEE Transactions on Cognitive and Developmental Systems |
2020 | |
卷号 | 暂无期号:暂无页码:暂无 |
摘要 | The musculoskeletal robot is a promising direction of the next-generation robots. However, current control methods of musculoskeletal robots lack multi-tasks learning ability, great generalization, and biological plausibility. In this article, a motor-cortex-like recurrent neural network (RNN) and a reward modulated multi-tasks learning method are proposed. First, inspired by dynamic system hypothesis of motor cortex, the RNN is introduced to transform movement targets into muscle excitations. The condition that makes a RNN generate motor-cortex-like consistent population response is investigated. Second, a reward modulated multi-tasks learning method of such a RNN is proposed. In the experiments, the control of a musculoskeletal system is realized with multi-tasks learning ability, great generalization, and robustness for noises. Furthermore, the RNN and muscle excitations demonstrate motor-cortex-like consistent population response and human-like muscle synergies respectively. Therefore, the proposed method has better performance and biological plausibility, and verifies the neural mechanisms in the robotic research. |
关键词 | Biologically inspired Musculoskeletal system Neuromuscular control, Motor cortex Muscle synergy Recurrent neural network |
收录类别 | SCI |
七大方向——子方向分类 | 类脑模型与计算 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44406 |
专题 | 多模态人工智能系统全国重点实验室_机器人理论与应用 |
通讯作者 | Hong Qiao |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China 3.Beijing Key Laboratory of Research and Application for Robotic Intelligence of Hand-Eye-Brain Interaction, Beijing, 100190, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jiahao Chen,Hong Qiao. Motor-Cortex-Like Recurrent Neural Network and Multi-Tasks Learning for the Control of Musculoskeletal Systems[J]. IEEE Transactions on Cognitive and Developmental Systems,2020,暂无(暂无):暂无. |
APA | Jiahao Chen,&Hong Qiao.(2020).Motor-Cortex-Like Recurrent Neural Network and Multi-Tasks Learning for the Control of Musculoskeletal Systems.IEEE Transactions on Cognitive and Developmental Systems,暂无(暂无),暂无. |
MLA | Jiahao Chen,et al."Motor-Cortex-Like Recurrent Neural Network and Multi-Tasks Learning for the Control of Musculoskeletal Systems".IEEE Transactions on Cognitive and Developmental Systems 暂无.暂无(2020):暂无. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Motor-Cortex-Like Re(1958KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Jiahao Chen]的文章 |
[Hong Qiao]的文章 |
百度学术 |
百度学术中相似的文章 |
[Jiahao Chen]的文章 |
[Hong Qiao]的文章 |
必应学术 |
必应学术中相似的文章 |
[Jiahao Chen]的文章 |
[Hong Qiao]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论