SIA OpenIR  > 空间自动化技术研究室
基于交叉熵优化的高斯混合模型运动编码
Alternative TitleEncoding Motor Skills with Gaussian Mixture Models Optimized by the Cross Entropy Method
张会文1,2; 张伟1; 周维佳1
Department空间自动化技术研究室
Source Publication机器人
ISSN1002-0446
2018
Volume40Issue:4Pages:569-576
Indexed ByEI ; CSCD
EI Accession number20184406012590
CSCD IDCSCD:6292386
Contribution Rank1
Keyword技能学习 模仿学习 交叉熵 任务参数 运动表征 混合模型
Abstract

针对模仿学习中运动的表征和泛化问题,提出了交叉熵优化算法,用于混合模型参数的推断.该算法易于实施、计算效率高.更重要的是,它能够自动确定混合模型中最优成分的个数.为了产生泛化的运动轨迹,提出了交叉熵回归算法.为了进一步提高这种算法对动态环境的适应能力,引入了任务参数化的概念并提出了任务参数交叉熵回归算法.最后设计了一个新颖的锤击任务,验证了所提出的算法在理论上的正确性和优越性.基于机器人物理仿真软件Gazebo的仿真实验表明了算法在实际应用中的可行性.

Other Abstract

Aiming at the movement representation and generalization problems in imitation learning, a cross entropy optimization algorithm is proposed to infer parameters in mixture models. The proposed algorithm is easy to implement and computationally efficient. More importantly, it can automatically determine the optimal component number in the mixture models. In order to produce generalized motion trajectories, a cross entropy regression algorithm is proposed. To further improve the adaptability of the algorithm in dynamic environments, the concept of task parametrization is introduced and a task-parameterized cross entropy regression algorithm is proposed. Finally, a novel hammer-over-a-nail task is designed, which verifies the theoretical correctness and superiority of the proposed methods. Simulation experiments based on robot physical simulation software Gazebo show the feasibility of the proposed algorithms in piratical applications.

Language中文
Citation statistics
Cited Times:1[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/22311
Collection空间自动化技术研究室
Corresponding Author张会文
Affiliation1.中国科学院沈阳自动化研究所机器人学国家重点实验室
2.中国科学院大学
Recommended Citation
GB/T 7714
张会文,张伟,周维佳. 基于交叉熵优化的高斯混合模型运动编码[J]. 机器人,2018,40(4):569-576.
APA 张会文,张伟,&周维佳.(2018).基于交叉熵优化的高斯混合模型运动编码.机器人,40(4),569-576.
MLA 张会文,et al."基于交叉熵优化的高斯混合模型运动编码".机器人 40.4(2018):569-576.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于交叉熵优化的高斯混合模型运动编码.p(608KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[张会文]'s Articles
[张伟]'s Articles
[周维佳]'s Articles
Baidu academic
Similar articles in Baidu academic
[张会文]'s Articles
[张伟]'s Articles
[周维佳]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[张会文]'s Articles
[张伟]'s Articles
[周维佳]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于交叉熵优化的高斯混合模型运动编码.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.