基于5G的视觉辅助BDS移动机器人融合定位算法

doi:10.11896/JsJkx.190400156

摘要/Abstract

摘要： 文中创新地提出了一种借助5G“宽带云信息”视觉图像处理辅助BDS来估计移动机器人位置,进而消除误差提高精度的方法。通过改进金字塔LK算法估计光流速度,从而精确得到移动机器人速度,并由手机加速度传感器提供加速度值,由北斗接收机提供粗略的移动机器人三维位置信息,并利用改进的卡尔曼滤波器进行数据融合。改进路径首先采用小波神经网络对卡尔曼滤波器进行监督控制,然后进一步采用改进的梯度下降法对小波神经网络权值和参数进行学习和训练,最后更进一步运用PSO与GA的组合算法来对小波神经网络的权值和阈值进行修正,以期进一步提升卡尔曼滤波器性能,突出机器人视觉定位方式累积误差通过BDS来矫正的优点,显著提高了特殊恶劣环境下组合导航定位的精度与可靠性。所提方法对当前BDS和5G技术在移动机器人领域的深入应用研究具有重要的参考价值。

关键词: 改进卡尔曼, 视觉图像处理, 数据融合, 移动机器人

Abstract: This paper presents an innovative method to estimate the position of mobile robot with 5G “broadband cloud information” visual image processing aided by BDS,so as to eliminate errors to improve accuracy.By improving the Pyramid LK algorithm to estimate the optical flow velocity,the mobile robot speed can be accurately obtained,and the acceleration value is providedby the mobile phone acceleration sensor,and the three-dimensional position information of the mobile robot can be roughly provided by the Beidou receiver.The improved Kalman filter is used for data fusion.The improved path is first supervised by the wavelet neural network.Then the improved gradient descent method is used to study and train the weights and parameters of the wavelet neural network.Finally,the combination algorithm of PSO and GA is further used to correct the weights and thresholds of the wavelet neural network with a view to further improve the performance of Kalman filter and highlight the advantages of the cumulative error of the robot visual positioning method corrected by BDS.It improves the accuracy and reliability of integrated navigation and positioning in special harsh environment,and has important reference value for the in-depth research of BDS and 5G technology in the field of mobile robots.

Key words: Data fusion, Improved Kalman filter algorithm, Mobile robot, Visual image processing

中图分类号:

TP399

马虹. 基于5G的视觉辅助BDS移动机器人融合定位算法[J]. 计算机科学, 2020, 47(6A): 631-633. https://doi.org/10.11896/JsJkx.190400156

MA Hong. Fusion Localization Algorithm of Visual Aided BDS Mobile Robot Based on 5G[J]. Computer Science, 2020, 47(6A): 631-633. https://doi.org/10.11896/JsJkx.190400156

参考文献

[1] 周牧,王斌,田增山,等.室内BLE/MEMS跨楼层融合定位算法.通信学报,2017(5):1-10.
[2] 徐国保.智能移动机器人技术现状及展望.机器人技术与应用,2017(2):29-34.
[3] 王洪涛.基于北斗卫星导航系统的移动机器人定位技术及应用.哈尔滨:哈尔滨工程大学,2014.
[4] 李卫东,贾洪明,冯祥雨.基于扩展卡尔曼滤波的列车定位.大连交通大学学报,2015(6):102-103.
[5] 李卫东,黄晨阳,刘杨,等.基于PSO小波神经网络辅助卡尔曼滤波的BDS/INS定位.自动化仪表,2018(1):76-77,39.
[6] HU Z T,YUAN G Y,HU Y M.Training method of neural net-work based on cubature Kalman filter.Control and Decision,2016,31(2):355-360.
[7] SISWANTORO J,PRABUWONO A S,ABDULLAH A.Linear model based on Kalman Filter for improving neural network classification performance.Expert System with Application,2016,49(15):112-122.
[8] 王慧,王光宇,潘德文.基于改进粒子群算法的移动机器人路径规划.传感器与微系统,2017,36(5):77-79.
[9] VIDAL C,JEDYNAK B.Derving Optimal Template—Matching Algorithm from Probabilistic Image Models.International Journal of Computer Vision,2010,88(2):189-213.
[10] 王亮.光流技术及其在运动目标检测和跟踪中的应用研究.长沙:国防科技大学,2007.
[11] BARRON J L,FLEET D J,BEAUCHEMIN S S,et al.Perfor-mance of optical flow techniques.Internation Journal of Computer Vision,1994,12(1):73-77.

相关文章 15

[1]	陈明鑫, 张钧波, 李天瑞. 联邦学习攻防研究综述 Survey on Attacks and Defenses in Federated Learning 计算机科学, 2022, 49(7): 310-323. https://doi.org/10.11896/jsjkx.211000079
[2]	杨斐斐, 沈思妤, 申德荣, 聂铁铮, 寇月. 面向数据融合的多粒度数据溯源方法 Method on Multi-granularity Data Provenance for Data Fusion 计算机科学, 2022, 49(5): 120-128. https://doi.org/10.11896/jsjkx.210300092
[3]	周新民, 胡宜桂, 刘文洁, 孙荣俊. 基于多模态多层级数据融合方法的城市功能识别研究 Research on Urban Function Recognition Based on Multi-modal and Multi-level Data Fusion Method 计算机科学, 2021, 48(9): 50-58. https://doi.org/10.11896/jsjkx.210500220
[4]	陈继清, 谭成志, 莫荣现, 王志奎, 吴家华, 赵超阳. 基于人工势场的A^算法的移动机器人路径规划 Path Planning of Mobile Robot with A^ Algorithm Based on Artificial Potential Field 计算机科学, 2021, 48(11): 327-333. https://doi.org/10.11896/jsjkx.200900170
[5]	王梓强, 胡晓光, 李晓筱, 杜卓群. 移动机器人全局路径规划算法综述 Overview of Global Path Planning Algorithms for Mobile Robots 计算机科学, 2021, 48(10): 19-29. https://doi.org/10.11896/jsjkx.200700114
[6]	张俊, 王杨, 李坤豪, 李昌, 赵传信. 基于流形学习的多源传感器体域网数据融合模型 Multi-source Sensor Body Area Network Data Fusion Model Based on Manifold Learning 计算机科学, 2020, 47(8): 323-328. https://doi.org/10.11896/jsjkx.191000012
[7]	黄婷婷, 冯锋. 无线传感器网络异构数据融合模型优化研究 Study on Optimization of Heterogeneous Data Fusion Model in Wireless Sensor Network 计算机科学, 2020, 47(11A): 339-344. https://doi.org/10.11896/jsjkx.200100109
[8]	陈骏岭, 秦小麟, 李星罗, 周杨淏, 鲍斌国. 基于人工势场法的多机器人协同避障 Multi-robot Collaborative Obstacle Avoidance Based on Artificial Potential Field Method 计算机科学, 2020, 47(11): 220-225. https://doi.org/10.11896/jsjkx.190900026
[9]	蔡莉, 李英姿, 江芳, 梁宇. 面向城市热点区域的不平衡数据聚类挖掘研究 Study on Clustering Mining of Imbalanced Data Fusion Towards Urban Hotspots 计算机科学, 2019, 46(8): 16-22. https://doi.org/10.11896/j.issn.1002-137X.2019.08.003
[10]	柴慧敏, 方敏, 吕少楠. 基于态势评估技术的移动机器人局部路径规划 Local Path Planning of Mobile Robot Based on Situation Assessment Technology 计算机科学, 2019, 46(4): 210-215. https://doi.org/10.11896/j.issn.1002-137X.2019.04.033
[11]	杨思星, 郭艳, 李宁, 孙保明, 钱鹏. 基于数据融合的压缩感知多目标定位算法 Compressive Sensing Multi-target Localization Algorithm Based on Data Fusion 计算机科学, 2018, 45(9): 161-165. https://doi.org/10.11896／j.issn.1002-137X.2018.09.026
[12]	琚春华, 邹江波, 傅小康. 融入区块链技术的大数据征信平台的设计与应用研究 Design and Application of Big Data Credit Reporting Platform Integrating Blockchain Technology 计算机科学, 2018, 45(11A): 522-526.
[13]	刘沛丰,王坚. 一种基于抗差EKF的移动机器人定位技术 Algorithm of SLAM Based on Robust EKF 计算机科学, 2017, 44(Z6): 115-118. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.025
[14]	高迪,徐峥,刘云淮. 面向公共安全数据处理的浪涌模型研究应用 Data Surge Models for Public Security Data Processing and Its Application in Unity of Security System 计算机科学, 2017, 44(Z6): 342-347. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.078
[15]	刘洁,赵海芳,周德廉. 一种改进量子行为粒子群优化算法的移动机器人路径规划 Improved Quantum Behaved Particle Swarm Optimization Algorithm for Mobile Robot Path Planning 计算机科学, 2017, 44(Z11): 123-128. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.025

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed