• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于标志物的机器人定位机器学习方法在机器人工厂 4.0 竞赛中的应用。

A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition.

机构信息

Department of Electronics (DAELN), Universidade Tecnológica Federal do Paraná (UTFPR), Curitiba 80230-901, Brazil.

Research Center in Digitalization and Intelligent Robotics (CeDRI), Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal.

出版信息

Sensors (Basel). 2023 Mar 15;23(6):3128. doi: 10.3390/s23063128.

DOI:10.3390/s23063128
PMID:36991840
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10054436/
Abstract

Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.

摘要

本地化是移动机器人中的一项关键技能，因为机器人需要做出合理的导航决策才能完成任务。有许多方法可以实现本地化，但人工智能可以作为基于模型计算的传统本地化技术的一种有趣替代方案。这项工作提出了一种机器学习方法来解决 RobotAtFactory 4.0 竞赛中的本地化问题。其想法是获取车载摄像头相对于基准标记（ArUco）的相对姿态，然后使用机器学习来估计机器人的姿态。该方法在模拟中得到了验证。测试了几种算法，结果表明使用随机森林回归器的效果最好，误差在毫米级。所提出的解决方案的结果与解决 RobotAtFactory 4.0 场景中的本地化问题的解析方法一样高，并且具有不需要像解析方法那样明确知道基准标记的确切位置的优势。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/79b7628ddcba/sensors-23-03128-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/b37bdaf18d30/sensors-23-03128-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/7389091fe243/sensors-23-03128-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/54b6833571bc/sensors-23-03128-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/3511d141ac4d/sensors-23-03128-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/cbaebf891dba/sensors-23-03128-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/2bd0a498b82b/sensors-23-03128-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/bf57f0d545a5/sensors-23-03128-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/145e99ead5f2/sensors-23-03128-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/79b7628ddcba/sensors-23-03128-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/b37bdaf18d30/sensors-23-03128-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/7389091fe243/sensors-23-03128-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/54b6833571bc/sensors-23-03128-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/3511d141ac4d/sensors-23-03128-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/cbaebf891dba/sensors-23-03128-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/2bd0a498b82b/sensors-23-03128-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/bf57f0d545a5/sensors-23-03128-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/145e99ead5f2/sensors-23-03128-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9364/10054436/79b7628ddcba/sensors-23-03128-g009.jpg

相似文献

1
A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition.基于标志物的机器人定位机器学习方法在机器人工厂 4.0 竞赛中的应用。
Sensors (Basel). 2023 Mar 15;23(6):3128. doi: 10.3390/s23063128.
2
A robot localization proposal for the RobotAtFactory 4.0: A novel robotics competition within the Industry 4.0 concept.针对“工厂机器人 4.0”的一种机器人定位方案：工业 4.0 概念下的一项新型机器人竞赛。
Front Robot AI. 2022 Nov 15;9:1023590. doi: 10.3389/frobt.2022.1023590. eCollection 2022.
3
Analytical Models for Pose Estimate Variance of Planar Fiducial Markers for Mobile Robot Localisation.平面基准标记位姿估计方差的分析模型及其在移动机器人定位中的应用。
Sensors (Basel). 2023 Jun 20;23(12):5746. doi: 10.3390/s23125746.
4
Social Robot Navigation Tasks: Combining Machine Learning Techniques and Social Force Model.社交机器人导航任务：机器学习技术与社会力模型的结合。
Sensors (Basel). 2021 Oct 26;21(21):7087. doi: 10.3390/s21217087.
5
Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach.基于Wi-Fi的室内定位与导航：一种机器人辅助的混合深度学习方法。
Sensors (Basel). 2023 Jul 12;23(14):6320. doi: 10.3390/s23146320.
6
A Semantic-Based Gas Source Localization with a Mobile Robot Combining Vision and Chemical Sensing.基于语义的移动机器人视觉与化学感知融合的气源定位
Sensors (Basel). 2018 Nov 28;18(12):4174. doi: 10.3390/s18124174.
7
Real-time neural network based camera localization and its extension to mobile robot control.
Int J Neural Syst. 1997 Jun;8(3):279-93. doi: 10.1142/s012906579700029x.
8
Comparison of Graph Fitting and Sparse Deep Learning Model for Robot Pose Estimation.图形拟合与稀疏深度学习模型在机器人位姿估计中的比较。
Sensors (Basel). 2022 Aug 29;22(17):6518. doi: 10.3390/s22176518.
9
Smart Artificial Markers for Accurate Visual Mapping and Localization.用于精确视觉映射和定位的智能人工标记
Sensors (Basel). 2021 Jan 18;21(2):625. doi: 10.3390/s21020625.
10
Automated fiducial marker detection and localization in volumetric computed tomography images: a three-step hybrid approach with deep learning.容积计算机断层扫描图像中自动基准标记检测与定位：一种基于深度学习的三步混合方法
J Med Imaging (Bellingham). 2021 Mar;8(2):025002. doi: 10.1117/1.JMI.8.2.025002. Epub 2021 Apr 28.

本文引用的文献

1
A robot localization proposal for the RobotAtFactory 4.0: A novel robotics competition within the Industry 4.0 concept.针对“工厂机器人 4.0”的一种机器人定位方案：工业 4.0 概念下的一项新型机器人竞赛。
Front Robot AI. 2022 Nov 15;9:1023590. doi: 10.3389/frobt.2022.1023590. eCollection 2022.
2
Systematic Mapping Literature Review of Mobile Robotics Competitions.系统地梳理移动机器人竞赛的文献综述。
Sensors (Basel). 2022 Mar 10;22(6):2160. doi: 10.3390/s22062160.
3
A Recursive Algorithm for Indoor Positioning Using Pulse-Echo Ultrasonic Signals.
基于回波脉冲超声波信号的室内定位递归算法。
Sensors (Basel). 2020 Sep 4;20(18):5042. doi: 10.3390/s20185042.
4
Gradient boosting machines, a tutorial.梯度提升机，教程。
Front Neurorobot. 2013 Dec 4;7:21. doi: 10.3389/fnbot.2013.00021. eCollection 2013.
5
A logical calculus of the ideas immanent in nervous activity. 1943.神经活动中内在思想的逻辑演算。1943年。
Bull Math Biol. 1990;52(1-2):99-115; discussion 73-97.