移动机器人多传感器数据融合方法研究*

doi:10.16731/j.cnki.1671-3133.2024.07.009

现代制造工程 ›› 2024, Vol. 526 ›› Issue (7): 69-76.doi: 10.16731/j.cnki.1671-3133.2024.07.009

移动机器人多传感器数据融合方法研究^*

冯婧¹, 魏航信¹, 岳高峰², 王煜坤¹, 秦乐¹, 席文奎¹, 孙文¹

1 西安石油大学机械工程学院,西安 710065;
2 西安交通大学网络空间安全学院,西安 710049

收稿日期:2023-11-13 出版日期:2024-07-18 发布日期:2024-07-30
通讯作者: 魏航信,博士,教授,主要研究方向为机器人控制、机器学习。E-mail:weihangxin@xsyu.edu.cn
作者简介:冯婧,硕士研究生,主要研究方向为机器学习、多传感器数据融合。E-mail:183623619@qq.com
基金资助:
*陕西省自然科学基础研究计划项目(2022-JQ571);陕西省厅市联动重点项目(2022GD-TSLD-22)

Research on the method of multi-sensor data fusion for mobile robots

FENG Jing¹, WEI Hangxin¹, YUE Gaofeng², WANG Yukun¹, QIN Le¹, XI Wenkui¹, SUN Wen¹

1 Mechanical Engineering College,Xi'an Shiyou University,Xi'an 710065,China;
2 School of Cyber Science and Engineering,Xi'an Jiaotong University,Xi'an 710049,China

Received:2023-11-13 Online:2024-07-18 Published:2024-07-30

摘要/Abstract

摘要： 多传感器数据融合技术能够更好地解决智能设备产生的数据不兼容问题,提高设备运行效率和生产力。现有方法缺乏高性能表现以及未考虑数据隐私保护问题,将联邦学习引入多传感器数据融合中,联邦学习局部模型采用门控循环单元(Gated Recurrent Unit,GRU)算法解决多传感器数据拟合问题,首次设计了一种在时间域和空间域上并行的立体式多传感器数据融合方法,该方法既具备优异的融合性能,又保证了各客户端数据的隐私性。实验结果表明了该方法的正确性与合理性,并在鲁棒性方面呈现出优势。

关键词: 移动机器人, 多传感器, 数据融合, 联邦学习

Abstract: Multi-sensor data fusion technology can better solve the problem of data incompatibility generated by smart devices,improve device operational efficiency and productivity. Existing methods lack high-performance performance and do not consider data privacy protection issues. It innovatively introduced federated learning into multi-sensor data fusion. The federated learning local model used the Gated Recurrent Unit (GRU) algorithm to solve the multi-sensor data fitting problem. A novel parallel stereoscopic multi-sensor data fusion method was designed for the first time,which has excellent fusion performance and ensures the privacy of each client′s data. The experimental results demonstrate the correctness and rationality of this method,as well as its advantages in robustness.

Key words: mobile robots, multi-sensor, data fusion, federated learning

中图分类号:

TP391
TH741

冯婧, 魏航信, 岳高峰, 王煜坤, 秦乐, 席文奎, 孙文. 移动机器人多传感器数据融合方法研究^*[J]. 现代制造工程, 2024, 526(7): 69-76.

FENG Jing, WEI Hangxin, YUE Gaofeng, WANG Yukun, QIN Le, XI Wenkui, SUN Wen. Research on the method of multi-sensor data fusion for mobile robots[J]. Modern Manufacturing Engineering, 2024, 526(7): 69-76.

参考文献

[1] 曹风魁,庄严,闫飞,等.移动机器人长期自主环境适应研究进展和展望[J].自动化学报,2020,46(2):205-221.
[2] 冯肖亮,文成林,刘伟峰,等.基于多传感器的序贯式融合有限域H∞滤波方法[J].自动化学报,2013,39(9):1523-1532.
[3] 罗本成,原魁,陈晋龙,等.一种基于不确定分析的多传感器信息动态融合方法[J].自动化学报,2004(3):407-415.
[4] ASACHI M,ALONSO C M.Multi-sensors data fusion for monitoring of powdered and granule products:current status and future perspectives[J].Advanced Powder Technology,2023,34(7):104055.
[5] GUO L,ZHANG M,SUN L.Environmental perception of mobile robot based on multi-sensors data fusion[J].International Journal of Information Acquisition,2006,3(4):311-319.
[6] ZHAO X,LUO Q,HAN B.Survey on robot multi-sensor information fusion technology[C]//2008 7th World Congress on Intelligent Control and Automation.Chongqing,China:IEEE,2008:5019-5023.
[7] KERMORGANT O,CHAUMETTE F.Multi-sensor data fusion in sensor-based control:application to multi-camera visual servoing[C]//2011 IEEE International Conference on Robotics and Automation.Shanghai,China:IEEE,2011:4518-4523.
[8] LIU B,ZHANG F,QU X.A method for improving the pose accuracy of a robot manipulator based on multi-sensor combined measurement and data fusion[J].Sensors,2015,15(4):7933-7952.
[9] HAGE J,NAJJAR M E,POMORSKI D.Multi-sensor fusion approach with fault detection and exclusion based on the kullback-Leibler divergence:application on collaborative multi-robot system[J].Information Fusion,2017,37:61-76.
[10] LIN K,LI Y,SUN J,et al.Multi-sensor fusion for body sensor network in medical human-robot interaction scenario[J].Information Fusion,2020,57:15-26.
[11] XING H,LIU Y,GUO S,et al.A multi-sensor fusion self-localization system of a miniature underwater robot in structured and GPS-denied environments[J].IEEE Sensors Journal,2021,21(23):27136-27146.
[12] LUO R C,LIN M H.Robot multi-sensor fusion and integration:optimum estimation of fused sensor data[C]//The Proceedings of 1988 IEEE International Conference on Robotics and Automation.Philadelphia,PA,USA:IEEE,1988:1076-1081.
[13] PARRER L E, SCHNEIDER F E, SCHULTZ A C. Multi-robot systems:from swarms to intelligent automata[M].Hingham,MA:Kluwer Academic Publishers,2002.
[14] LI C,SUN H,YE P.Multi-sensor fusion localization algorithm for outdoor mobile robot[C]//Journal of Physics:Conference Series.Xi'an,China:IOP Publishing,2020.
[15] 张晓娟,王文强,唐长乐.中美政府数据开放和个人隐私保护的政策法规研究[J].情报理论与实践,2016,39(1):38-43.
[16] 黄如花,刘龙.我国政府数据开放中的个人隐私保护问题与对策[J].图书馆,2017(10):1-5.
[17] GHORASHI S,ZIA T,BEWONG M,et al.An Analytical Review of Industrial Privacy Frameworks and Regulations for Organisational Data Sharing[J].Applied Sciences,2023,13(23):12727.
[18] 李国杰,程学旗.大数据研究:未来科技及经济社会发展的重大战略领域——大数据的研究现状与科学思考[J].中国科学院院刊,2012,27(6):647-657.
[19] 周传鑫,孙奕,汪德刚,等.联邦学习研究综述[J].网络与信息安全学报,2021,7(5):77-92.
[20] 李少波,杨磊,李传江,等.联邦学习概述:技术、应用及未来[J].计算机集成制造系统,2022,28(7):2119-2138.
[21] SMITH V,CHIANG C K,SANJABI M,et al.Federated multi-task learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.Long Beach,CA,United states:IEEE,2017:4427-4437.
[22] HARD A,RAO K,MATHEWS R,et al.Federated learning for mobile keyboard prediction[J].arXiv preprint arXiv,2018,11:4-7.
[23] CALDAS S,DUDDU S M K,WU P,et al.Leaf:A benchmark for federated settings[J].arXiv preprint arXiv,2018,12.
[24] YANG Q,LIU Y,CHEN T,et al.Federated machine learning:Concept and applications[J].Associationfor Computing Machinery Transactions on Intelligent Systems and Technology,2019,10(2):1-19.
[25] SATTLER F,WIEDEMANN S,MÜLLER K R,et al.Robust and communication-efficient federated learning from non-iid data[J].IEEE transactions on neural networks and learning systems,2019,31(9):3400-3413.
[26] WANG H,YUROCHKIN M,SUN Y,et al.Federated learning with matched averaging[J].arXiv preprint arXiv,2020,2.
[27] REDDI S,CHARLES Z,ZAHEER M,et al.Adaptive federated optimization[J].arXiv preprint arXiv:2003.00295,2020.
[28] 邹波,张华,姜军.多传感信息融合的改进扩展卡尔曼滤波定姿[J].计算机应用研究,2014,31(4):1035-1038,1042.
[29] 杨小军,潘泉,梁彦,等.基于粒子滤波和检测信息的多传感器融合跟踪[J].信息与控制,2005(3):356-359.

移动机器人多传感器数据融合方法研究^*

Research on the method of multi-sensor data fusion for mobile robots

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	田颖, 徐荣英. 球形移动机器人变形机构结构设计研究综述^*[J]. 现代制造工程, 2025, 538(7): 139-148.
[2]	付丹丹, 李波. 基于改进RRT^与DWA融合的移动机器人路径规划算法研究^[J]. 现代制造工程, 2025, 535(4): 91-97.
[3]	李丹丹, 朱石磊, 李仲康, 介百坤, 王宏. 基于改进变色龙群算法的移动机器人路径规划^*[J]. 现代制造工程, 2024, 528(9): 40-45.
[4]	梁彪, 周德强, 盛卫锋, 左文娟, 何长江, 奚青, 陈曲燕. 基于分数阶滑模控制的AGV纠偏系统研究^*[J]. 现代制造工程, 2024, 527(8): 51-60.
[5]	方文凯, 廖志高. 基于融合A^-蚁群优化算法的移动机器人全局优化^[J]. 现代制造工程, 2024, 526(7): 77-84.
[6]	纪有旺, 解乃军, 殷冬年. 基于数字孪生的移动机器人可视化监控系统^*[J]. 现代制造工程, 2024, 522(3): 23-30.
[7]	朱敏, 胡若海, 卞京. 基于改进蚁群算法的移动机器人路径规划[J]. 现代制造工程, 2024, 522(3): 38-44.
[8]	徐胜, 沙鑫美, 苏铭. 移动机器人沿墙算法研究综述[J]. 现代制造工程, 2024, 521(2): 150-158.
[9]	唐宏伟, 罗佳强, 邓嘉鑫, 王军权, 石书琪. 基于学习机制蚁群算法的移动机器人路径规划^*[J]. 现代制造工程, 2024, 531(12): 48-53.
[10]	殷才茗，王文瑞，鲁方林，姜山，马娜，吴波. 基于联邦学习和改进多尺度ResNet的故障诊断[J]. 现代制造工程, 2023, 512(5): 127-134.
[11]	李广;孔飞飞;王逍遥;杜福洲;刘连喜. 基于多视觉传感器融合的装配过程质量移动智能检测技术研究[J]. 现代制造工程, 2023, 511(4): 116-123.
[12]	周宏根，董宝江，田崇顺，李国超，史肖娜，富艳玲，罗明镇，孙丽. 船用柴油机机体孔系平行度在机检测方法[J]. 现代制造工程, 2023, 519(12): 1-5.
[13]	杨博，刘树东，鲁维佳，潘玉恒. 改进遗传算法在机器人路径规划中的应用[J]. 现代制造工程, 2022, 501(6): 9-16.
[14]	袁福龙，朱建平. 基于改进蚁群算法的移动机器人最优路径规划[J]. 现代制造工程, 2021, 490(7): 38-47.
[15]	丁平，李贞辉，张林华，杨晓龙，刘爱华. 输电线巡检机器人障碍物定位与识别[J]. 现代制造工程, 2021, 485(2): 36-42.