Collaborative Robot Mapping using Spectral Graph Analysis

被引:6
作者
Bernreiter, Lukas [1 ]
Khattak, Shehryar [2 ]
Ott, Lionel [1 ]
Siegwart, Roland [1 ]
Hutter, Marco [2 ]
Cadena, Cesar [1 ]
机构
[1] Swiss Fed Inst Technol, Autonomous Syst Lab, CH-8092 Zurich, Switzerland
[2] Swiss Fed Inst Technol, Robot Syst Lab, CH-8092 Zurich, Switzerland
来源
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022) | 2022年
基金
瑞士国家科学基金会;
关键词
ROBUST; SLAM; MAXIMIZATION;
D O I
10.1109/ICRA46639.2022.9812102
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we deal with the problem of creating globally consistent pose graphs in a centralized multi-robot SLAM framework. For each robot to act autonomously, individual onboard pose estimates and maps are maintained, which are then communicated to a central server to build an optimized global map. However, inconsistencies between onboard and server estimates can occur due to onboard odometry drift or failure. Furthermore, robots do not benefit from the collaborative map if the server provides no feedback in a computationally tractable and bandwidth-efficient manner. Motivated by this challenge, this paper proposes a novel collaborative mapping framework to enable accurate global mapping among robots and server. In particular, structural differences between robot and server graphs are exploited at different spatial scales using graph spectral analysis to generate necessary constraints for the individual robot pose graphs. The proposed approach is thoroughly analyzed and validated using several real-world multi-robot field deployments where we show improvements of the onboard system up to 90%.
引用
收藏
页码:3662 / 3668
页数:7
相关论文
共 35 条
[1]  
[Anonymous], 2021, IEEE T ROBOTICS, DOI DOI 10.1080/10494820.2021.1931346
[2]   Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback [J].
Bloesch, Michael ;
Burri, Michael ;
Omari, Sammy ;
Hutter, Marco ;
Siegwart, Roland .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2017, 36 (10) :1053-1072
[3]  
Brunskill E, 2007, 2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, P3497
[4]   The EuRoC micro aerial vehicle datasets [J].
Burri, Michael ;
Nikolic, Janosch ;
Gohl, Pascal ;
Schneider, Thomas ;
Rehder, Joern ;
Omari, Sammy ;
Achtelik, Markus W. ;
Siegwart, Roland .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2016, 35 (10) :1157-1163
[5]   Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs [J].
Chandra, Rohan ;
Guan, Tianrui ;
Panuganti, Srujan ;
Mittal, Trisha ;
Bhattacharya, Uttaran ;
Bera, Aniket ;
Manocha, Dinesh .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2020, 5 (03) :4882-4890
[6]  
Cunningham A, 2013, IEEE INT CONF ROBOT, P5220, DOI 10.1109/ICRA.2013.6631323
[7]   Graph-based subterranean exploration path planning using aerial and legged robots [J].
Dang, Tung ;
Tranzatto, Marco ;
Khattak, Shehryar ;
Mascarich, Frank ;
Alexis, Kostas ;
Hutter, Marco .
JOURNAL OF FIELD ROBOTICS, 2020, 37 (08) :1363-1388
[8]  
Deutsch I, 2016, 2016 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (IEEE RCAR), P567, DOI 10.1109/RCAR.2016.7784092
[9]   Kron Reduction of Graphs With Applications to Electrical Networks [J].
Doerfler, Florian ;
Bullo, Francesco .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2013, 60 (01) :150-163
[10]  
Dong J, 2015, IEEE INT CONF ROBOT, P5807, DOI 10.1109/ICRA.2015.7140012