机器人杯小型联赛（SSL）中具有避障功能的曲线踢球机制的神经网络设计

IF 3.1 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Journal of Intelligent & Robotic Systems Pub Date : 2024-08-20 DOI:10.1007/s10846-024-02140-0

Francisco A. B. Azevedo, Guilherme P. C. Leão, Marcos R. O. A. Maximo

{"title":"机器人杯小型联赛（SSL）中具有避障功能的曲线踢球机制的神经网络设计","authors":"Francisco A. B. Azevedo, Guilherme P. C. Leão, Marcos R. O. A. Maximo","doi":"10.1007/s10846-024-02140-0","DOIUrl":null,"url":null,"abstract":"<p>At the RoboCup, a robotics soccer tournament, the Small Size League (SSL) is one of its leagues. The thought of a mechanism in this league that could perform unpredictable kicks and passes inspired study into both the physical mechanism required to do it and the algorithms needed to make the most of it.By introducing new ideas and utilizing a Deep Neural Network, this work contributes by improving a prior algorithm that aims to carry out a real-time inversion of the non-linear ordinary differential equation (ODE) that models the ball’s path in order to determine the parameters to hit a target with a curved kick mechanism (DNN). New techniques are also presented. The two suggested DNN achieved accuracy levels of more than 92% in the outcomes of simulation runs in MATLAB.</p>","PeriodicalId":54794,"journal":{"name":"Journal of Intelligent & Robotic Systems","volume":"73 1","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural Network Design for a Curved Kicking Mechanism with Obstacle Avoidance in RoboCup Small Size League (SSL)\",\"authors\":\"Francisco A. B. Azevedo, Guilherme P. C. Leão, Marcos R. O. A. Maximo\",\"doi\":\"10.1007/s10846-024-02140-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>At the RoboCup, a robotics soccer tournament, the Small Size League (SSL) is one of its leagues. The thought of a mechanism in this league that could perform unpredictable kicks and passes inspired study into both the physical mechanism required to do it and the algorithms needed to make the most of it.By introducing new ideas and utilizing a Deep Neural Network, this work contributes by improving a prior algorithm that aims to carry out a real-time inversion of the non-linear ordinary differential equation (ODE) that models the ball’s path in order to determine the parameters to hit a target with a curved kick mechanism (DNN). New techniques are also presented. The two suggested DNN achieved accuracy levels of more than 92% in the outcomes of simulation runs in MATLAB.</p>\",\"PeriodicalId\":54794,\"journal\":{\"name\":\"Journal of Intelligent & Robotic Systems\",\"volume\":\"73 1\",\"pages\":\"\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Intelligent & Robotic Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s10846-024-02140-0\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Intelligent & Robotic Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10846-024-02140-0","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

摘要

在机器人杯足球赛（RoboCup）中，小规模联赛（SSL）是其中的一个联赛。通过引入新思路和利用深度神经网络，这项工作改进了先前的算法，旨在对建模球路径的非线性常微分方程（ODE）进行实时反演，以确定用曲线踢球机制（DNN）击中目标的参数。此外，还介绍了新技术。这两种建议的 DNN 在 MATLAB 中模拟运行的结果达到了 92% 以上的准确率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Neural Network Design for a Curved Kicking Mechanism with Obstacle Avoidance in RoboCup Small Size League (SSL)

At the RoboCup, a robotics soccer tournament, the Small Size League (SSL) is one of its leagues. The thought of a mechanism in this league that could perform unpredictable kicks and passes inspired study into both the physical mechanism required to do it and the algorithms needed to make the most of it.By introducing new ideas and utilizing a Deep Neural Network, this work contributes by improving a prior algorithm that aims to carry out a real-time inversion of the non-linear ordinary differential equation (ODE) that models the ball’s path in order to determine the parameters to hit a target with a curved kick mechanism (DNN). New techniques are also presented. The two suggested DNN achieved accuracy levels of more than 92% in the outcomes of simulation runs in MATLAB.

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

Journal of Intelligent & Robotic Systems 工程技术-机器人学

CiteScore

7.00

自引率

9.10%

发文量

219

审稿时长

6 months

期刊介绍： The Journal of Intelligent and Robotic Systems bridges the gap between theory and practice in all areas of intelligent systems and robotics. It publishes original, peer reviewed contributions from initial concept and theory to prototyping to final product development and commercialization. On the theoretical side, the journal features papers focusing on intelligent systems engineering, distributed intelligence systems, multi-level systems, intelligent control, multi-robot systems, cooperation and coordination of unmanned vehicle systems, etc. On the application side, the journal emphasizes autonomous systems, industrial robotic systems, multi-robot systems, aerial vehicles, mobile robot platforms, underwater robots, sensors, sensor-fusion, and sensor-based control. Readers will also find papers on real applications of intelligent and robotic systems (e.g., mechatronics, manufacturing, biomedical, underwater, humanoid, mobile/legged robot and space applications, etc.).