融合深度学习与粒子滤波的移动机器人重定位方法  

Mobile robot relocalization method fusing deep learning and particle filtering

作　　者：杨傲雷[1,2] 金宏宙 陈灵 费敏锐 Yang Aolei;Jin Hongzhou;Chen Ling;Fei Minrui(School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200444,China;Shanghai Key Laboratory of Power Station Automation Technology,Shanghai 200444,China;College of Engineering and Design,Hunan Normal University,Hunan 410081,China)

机构地区：[1]上海大学机电工程与自动化学院,上海200444 [2]上海市电站自动化技术重点实验室,上海200444 [3]湖南师范大学工程与设计学院,湖南410081

出　　处：《仪器仪表学报》2021年第7期226-233,共8页Chinese Journal of Scientific Instrument

基　　金：上海市自然科学基金(18ZR1415100);国家自然科学基金(61703262)项目资助。

摘　　要：为有效解决移动机器人重定位问题,提出一种融合深度学习和粒子滤波的机器人重定位方法。首先,提出了3自由度移动机器人重定位方法架构,主要包含重定位模型构建和机器人在线重定位两个递进阶段;其次,在PoseNet基础上提出并构建了针对3自由度移动机器人的重定位网络模型GPoseNet,并将由GPoseNet预测的位姿结果作为粒子滤波定位算法的初始化状态,支撑后续重定位过程;然后,提出了一种基于数据模型的机器人绑架状态判定方法,以确定是否启动重定位过程;最后,在公开数据集上与实际环境中做了大量实验验证了此方法,结果表明:GPoseNet模型能够保证一定的位置预测精度并提升了姿态角预测精度,机器人重定位成功率达到87%。In order to effectively solve the relocalization problem of mobile robot,a robot relocalization method fusing deep learning and particle filtering is proposed.Firstly,a 3-DOF mobile robot relocalization framework is proposed,which mainly includes two progressive stages:relocalization model construction and robot online relocalization.Secondly,a 3-DOF mobile robot relocalization network model,GPoseNet,is proposed and constructed based on PoseNet.The pose result predicted by GPoseNet is used as the initialization state of particle filter localization algorithm to support the subsequent relocalization process.Then,a data model based kidnapping state judging method is proposed to determine whether to start the relocalization process.Finally,a large number of experiments on public datasets and real environment were performed to verify the proposed method.The result shows that the GPoseNet model can guarantee a certain degree of location prediction accuracy and improve the pose angle prediction accuracy,the success rate of robot relocalization achieves 87%.

关 键 词：深度学习 位姿回归 粒子滤波定位 机器人绑架 重定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TH86[自动化与计算机技术—计算机科学与技术]