FloorplanNet: Learning Topometric Floorplan Matching for Robot Localization
2023
会议录名称PROCEEDINGS - IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
ISSN1050-4729
卷号2023-May
页码6168-6174
发表状态已发表
DOI10.1109/ICRA48891.2023.10160977
摘要

Given a building floorplan, humans can localize themselves by matching the observation of the environment with the floorplan using geometric, semantic, and topological clues. Inspired by this insight, this paper proposes a learning- based topometric robot localization method FloorplanNet, which implements a match between a metric robot map and the potentially inaccurate building floorplan in nonuniform scales and different shapes by semantic information. The method uses a novel Graph Neural Network to learn descriptors of nodes from topometric graphs generated from the input maps. We demonstrate that our method can match the 3D point cloud sub-map generated by the robot during the SLAM process with the 2D map. Furthermore, we apply our map-matching algorithm for real-world robot localization. We evaluate our method on several publicly available real-world datasets. Even though our network is solely trained using simulation data, our method demonstrates high robustness and effectiveness in real- world indoor environments and outperforms the existing SOTA map-matching algorithms. We further develop a simulator that automatically creates and annotates the required training data to train our neural networks. The method and simulator are released at: https://github.com/fengdelin/FloorplanNet.git © 2023 IEEE.

会议举办国UK
关键词Graph neural networks Indoor positioning systems Robot applications Different shapes Floorplans Geometric semantics Localization method Map-matching algorithm Matchings Real-world Robot localization Robot maps Semantics Information Localization Map Matching Graph Neural network
会议名称2023 IEEE International Conference on Robotics and Automation, ICRA 2023
会议地点London, United kingdom
会议日期May 29, 2023 - June 2, 2023
学科门类工学::计算机科学与技术(可授工学、理学学位)
URL查看原文
收录类别EI
语种英语
出版者Institute of Electrical and Electronics Engineers Inc.
EI入藏号20233514632785
EI主题词Semantics
EI分类号723.4 Artificial Intelligence ; 731.6 Robot Applications
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/325844
专题信息科学与技术学院
信息科学与技术学院_PI研究组_Sören Schwertfeger组
信息科学与技术学院_硕士生
信息科学与技术学院_博士生
作者单位
1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
2.Robotics and Auto-Driving Laboratory (RAL), Baidu Research
第一作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Delin Feng,Zhenpeng He,Jiawei Hou,et al. FloorplanNet: Learning Topometric Floorplan Matching for Robot Localization[C]:Institute of Electrical and Electronics Engineers Inc.,2023:6168-6174.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Delin Feng]的文章
[Zhenpeng He]的文章
[Jiawei Hou]的文章
百度学术
百度学术中相似的文章
[Delin Feng]的文章
[Zhenpeng He]的文章
[Jiawei Hou]的文章
必应学术
必应学术中相似的文章
[Delin Feng]的文章
[Zhenpeng He]的文章
[Jiawei Hou]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。