基于一阶原理的构造网络拓扑:在机器人逆动力学中的应用

F. Ledezma, S. Haddadin
{"title":"基于一阶原理的构造网络拓扑:在机器人逆动力学中的应用","authors":"F. Ledezma, S. Haddadin","doi":"10.1109/HUMANOIDS.2017.8246910","DOIUrl":null,"url":null,"abstract":"Modeling physical systems with neural networks (NN) requires expert architects to determine the best number of nodes, layers and activation functions. For complex systems, such as articulated robots, reported results are limited in accuracy and generalization capabilities. In this work, we introduce the concept FOPnet. It is based on first-order principles and system knowledge to determine topologies of parametrized operator networks that accurately model input-output mappings of physical systems. These topologies consist of meaningful building elements and connections as well as a reduced number of parameters that describe the variables' interdependencies. In this way, learning speed is boosted and the model's accuracy, precision and generalization power improved. We apply the methodology to a 7 degrees-of-freedom LWR4 manipulator and discuss the estimation and generalization capabilities of the network. Results are compared to conventional Feed Forward NN as well as a state-of-the-art Deep Recurrent NN. For the considered complex robot dynamics FOPnet was able to achieve a seven orders of magnitude smaller generalization RMSE.","PeriodicalId":143992,"journal":{"name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":"{\"title\":\"First-order-principles-based constructive network topologies: An application to robot inverse dynamics\",\"authors\":\"F. Ledezma, S. Haddadin\",\"doi\":\"10.1109/HUMANOIDS.2017.8246910\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Modeling physical systems with neural networks (NN) requires expert architects to determine the best number of nodes, layers and activation functions. For complex systems, such as articulated robots, reported results are limited in accuracy and generalization capabilities. In this work, we introduce the concept FOPnet. It is based on first-order principles and system knowledge to determine topologies of parametrized operator networks that accurately model input-output mappings of physical systems. These topologies consist of meaningful building elements and connections as well as a reduced number of parameters that describe the variables' interdependencies. In this way, learning speed is boosted and the model's accuracy, precision and generalization power improved. We apply the methodology to a 7 degrees-of-freedom LWR4 manipulator and discuss the estimation and generalization capabilities of the network. Results are compared to conventional Feed Forward NN as well as a state-of-the-art Deep Recurrent NN. For the considered complex robot dynamics FOPnet was able to achieve a seven orders of magnitude smaller generalization RMSE.\",\"PeriodicalId\":143992,\"journal\":{\"name\":\"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"29\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HUMANOIDS.2017.8246910\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HUMANOIDS.2017.8246910","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 29

摘要

用神经网络(NN)建模物理系统需要专家架构师来确定节点、层和激活函数的最佳数量。对于复杂的系统,如关节机器人,报告的结果在准确性和泛化能力方面是有限的。在这项工作中,我们引入了FOPnet的概念。它基于一阶原理和系统知识来确定参数化算子网络的拓扑结构,从而准确地模拟物理系统的输入-输出映射。这些拓扑包括有意义的建筑元素和连接,以及描述变量相互依赖关系的减少数量的参数。这样可以加快学习速度,提高模型的准确性、精密度和泛化能力。我们将该方法应用于一个7自由度的LWR4机械臂,并讨论了网络的估计和泛化能力。结果与传统的前馈神经网络以及最先进的深度递归神经网络进行了比较。对于考虑复杂的机器人动力学,FOPnet能够实现小7个数量级的泛化RMSE。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
First-order-principles-based constructive network topologies: An application to robot inverse dynamics
Modeling physical systems with neural networks (NN) requires expert architects to determine the best number of nodes, layers and activation functions. For complex systems, such as articulated robots, reported results are limited in accuracy and generalization capabilities. In this work, we introduce the concept FOPnet. It is based on first-order principles and system knowledge to determine topologies of parametrized operator networks that accurately model input-output mappings of physical systems. These topologies consist of meaningful building elements and connections as well as a reduced number of parameters that describe the variables' interdependencies. In this way, learning speed is boosted and the model's accuracy, precision and generalization power improved. We apply the methodology to a 7 degrees-of-freedom LWR4 manipulator and discuss the estimation and generalization capabilities of the network. Results are compared to conventional Feed Forward NN as well as a state-of-the-art Deep Recurrent NN. For the considered complex robot dynamics FOPnet was able to achieve a seven orders of magnitude smaller generalization RMSE.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信