室内移动机器人的SLAM算法综述

doi:10.11896/jsjkx.200700152

摘要/Abstract

摘要： SLAM(Simultaneous Localization and Mapping),即同时定位与地图构建,目前被广泛应用于机器人领域。SLAM算法使得机器人处于陌生环境时,能够通过自身搭载的传感器来感知环境信息并建立环境地图,并完成对自身位姿的计算,从而能够在未知环境中进行移动。随着研究者们对SLAM问题的深入研究,SLAM领域相关成果已非常丰富,但是有关室内场景SLAM的论述还不够系统。通过对现有的关于SLAM算法发展成果的总结和对比,对室内SLAM进行了综合性的阐述。首先介绍了SLAM的技术现状和室内场景SLAM在不同传感器下的分类问题;其次介绍了SLAM的经典框架;然后根据相关传感器种类的不同,简要介绍了不同传感器下常见的SLAM算法的原理,同时讨论了传统室内SLAM算法中存在的诸多局限性问题,引出了基于多传感器融合技术的SLAM和基于深度学习技术的SLAM两个研究方向;最后介绍了SLAM的未来发展趋势和应用领域。

关键词: 定位与建图, 多传感器, 激光雷达, 深度学习, 室内, 相机

Abstract: As a localization and map construction method,SLAM(Simultaneous Localization and Mapping) is widely used in the field of robots.SLAM algorithm enables the robot to perceive environmental information and establish environmental map through sensors carried by the robot itself in an unfamiliar environment,and calculate its own posture.In this way,the robot can move in an unknown environment.With the in-depth study of SLAM,the research results in the field of SLAM have been very rich.However,the discussion on indoor SLAM is not comprehensive enough.Through the summary and comparison of the exis-ting development results of the SLAM method,a comprehensive statement is shown.In this paper,the technical status of SLAM and the classification problem of SLAM under different sensors in indoor scenes are firstly introduced.Secondly,the classic framework of SLAM is revealed.Thirdly,the principles of SLAM algorithms with different sensors are described according to the different types of related sensors.Fourthly,the limitations of the traditional indoor SLAM algorithms are discussed and two research directions-SLAM based on multi-sensor fusion technology and SLAM based on deep learning technology are led out.Finally,the future development trend and application field of SLAM are suggested

Key words: Camera, Deep learning, Indoor, Lidar, Multi-sensor, Positioning and mapping

中图分类号:

TP242

田野, 陈宏巍, 王法胜, 陈兴文. 室内移动机器人的SLAM算法综述[J]. 计算机科学, 2021, 48(9): 223-234. https://doi.org/10.11896/jsjkx.200700152

TIAN Ye, CHEN Hong-wei, WANG Fa-sheng, CHEN Xing-wen. Overview of SLAM Algorithms for Mobile Robots[J]. Computer Science, 2021, 48(9): 223-234. https://doi.org/10.11896/jsjkx.200700152

参考文献

[1]LIU Z.Research status and future of mobile robot technology[J].Digital Technology and Application,2019,37(10):214-215.
[2]MA Z G,ZHAO Y G,LIU C Y,et al.Review of Research on Laser and Vision Fusion SLAM Method[J].Computer Measurement and Control,2019,27(3):1-6.
[3]SMITH R C,CHEESEMAN P.On the representation and estimation of spatial uncertainty[J].The International Journal of Robotics Research,1986,5(4):56-68.
[4]SCARAMUZZA D,CADENA C,LEONARD J,et al.Past,Pre-sent,and Future of Simultaneous Localization and Mapping:Toward the Robust-Perception Age[J].IEEE Transactions on Robotics,2016,32(6):1309-1332.
[5]LI Y T,MU R J,SHAN Y Z.A brief analysis of the development status of unmanned system vision SLAM technology[J/OL].Control and Decision,2020:1-10.http://kzyjc.alljournals.cn/ch/reader/download_new_edit_content.aspx?file_no=201908110000001&edit_id=20200106145046001&flag=2&year_id=&quarter_id=.
[6]LENAC K,KITANO A,CUPEC R,et al.Fast Planar Surface 3D SLAM Using LIDAR[J].Robotics and Autonomous Systems,2017,92:197-220.
[7]PIERZCHALA M,GIGUERE P,ASTRUP R.Mapping forests using an unmanned ground vehicle with 3D Lidar and graph-SLAM[J].Computer and Electronics in Agriculture,2018,145:217-225.
[8]DROSECHEL D,BEHNKE S.Efficient Continuous-TimeSLAM for 3D Lidar-Based Online Mapping[C]//2018 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2018:1-9.
[9]BELBACHIR N,NOORI N,AKDEMIR B.Real-Time VehicleLocalization using on-Board Visual SLAM for Detection and Tracking[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop(ICCVW).IEEE,2019:4291-4295.
[10]SCHNEIDER H,DYMCZYK M,FEHR M,et al.Maplab:An Open Framework for Research in Visual-Inertial Mapping and Localization[J].IEEE Robotics and Automation Letters,2019,8(29):1418-1425.
[11]DENG S Y,GUO C J.Research on real-time location and map construction method based on multi-sensor fusion[C]//Procee-dings of the 11th China Satellite Navigation Annual Conference-S13 Autonomous Navigation,Academic Exchange Center of China Satellite Navigation System Management Office.2020:6.
[12]ZHAO Y,LIU G L,TIAN G H,et al.A Summary of VisualSLAM Based on Deep Learning[J].Robot,2017,39(6):889-896.
[13]CHEN J Y,SHI Y C.Research progress of solid-state lidar[J].Opto-Electronic Engineering,2019,46(7):1-11.
[14]GAO X,ZHANG T.The fourteen lectures on visual SLAM[M].Beijing:Publishing House of Electronics Industry,2017:97-107.
[15]ZHAO L S,FENG Y,CAO Y.Optimization of SURF algorithm parameters in monocular visual positioning[J].Computer Technology and Development,2012,22(6):6-9.
[16]WANG X W,HE L L,ZHAO T.Research on Mobile Robot SLAM Based on Lidar and Binocular Vision[J].Journal of Transduction Technology,2018,31(3):394-399.
[17]PAN L H,TIAN F Q,YING W J,et al.Monocular camera-IMU external parameter automatic calibration and online estimation of visual-inertial navigation SLAM[J].Chinese Journal of Scientific Instrument,2019,40(6):56-67.
[18]FAN J B,SUN J,FAN H H,et al.Autonomous positioningmethod based on magnetometer,IMU and monocular vision[J].Overall Aerospace Technology,2019,3(6):39-45.
[19]LIU R J,WANG X S,ZHANG C,et al.A Summary of Visual SLAM Based on Deep Learning[J].Journal of System Simulation,2020,32(7):1244-1256.
[20]WU Z Y,ZHANG C,LIN Y.Optimal design of laser SLAMalgorithm based on RBPF[J].Computer Engineering,2020,46(7):294-299.
[21]WANG H,WANG P.Research and Implementation Based on RBPF-SLAM Algorithm[J].Computer Application System,2019,28(7):169-173.
[22]MAO S L,DI W,HAO Y D.Indoor 2D Laser SLAM on a Raspberry Pi-Based Mobile Robot[C]//2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics(IHMSC).2019.
[23]WONGSUWAN K,SUKVICHAI K.Generalizing correctivegradient refinement in RBPF for occupancy grid LIDAR SLAM[C]//2017 IEEE International Conference on Robotics and Bio-mimetics(ROBIO).IEEE,2017.
[24]ZHANG L,LIU Z Y,CAO J Y,et al.Cartographer algorithm and system realization based on enhanced pose fusion of swee-ping robot[J].Journal of Software,2020,31(9):1-13.
[25]WU C D,YAO J M,HU H L.Cartographer 2D SLAM algorithmresearch[J].Cable TV Technology,2018(4):20-22.
[26]SANTOS J M,PORTUGAL D,RUI P R.An evaluation of 2D SLAM techniques available in Robot Operating System[C]//IEEE International Symposium on Safety,Security and Rescue Robotics.IEEE,2014:1-6.
[27]HESS W,KOHLER D,RAPP H,et al.Real-time loop closure in2D lidar SLAM [C]//Proc of IEEE International Conference on Robotics and Automation.Piscataway,NJ:IEEE,2016:1271-1278.
[28]JIAN J Z,LI X.Design and Implementation of ROS-Based Autonomous Mobile Robot Positioning and Navigation System[C]//2019 18th International Symposium on Distributed Computing and Applications for Business Engineering and Science(DCABES).2019.
[29]KOHLBRECHER S,VON S O,MEYER J,et al,A flexible and scalable slam system with full 3d motion estimation[C]//2011 IEEE International Symposium on Safety,Security and Rescue Rootics.IEEE,2011:155-160.
[30]YU N,ZHANG B.An Improved Hector SLAM Algorithmbased on Information Fusion for Mobile Robot[C]//2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems(CCIS).IEEE,2019:279-284.
[31]QUAN M X,PU S H,LI G.Visual SLAM Review[J].Journal of Intelligent Systems,2016,11(6):768-776.
[32]LV L H.Summary of Vision-based Real-time Location and Map Reconstruction(V-SLAM)[J].New Technology,2019:67-70.
[33]DAVISON A J,REID I D,MOLTON N D,et al.Mono-SLAM:real-time single camera SLAM[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1052-1067.
[34]KLEIN G,MURRAY D.Parallel Tracking and Mapping forSmall AR Workspaces[C]//IEEE and ACM International Symposium on Mixed and Augmented Reality.2007:225-234.
[35]MUR-ARTAL R,MONTIEL J M M,TARDOS J D.ORB-SLAM:A Versatile and Accurate Monocular SLAM System[J].IEEE Transactions on Robotics,2015,31(5):1147-1163.
[36]LIU H M,ZHANG G F,BAO H J.Overview of simultaneouspositioning and map construction methods based on monocular vision[J].Journal of Computer Aided Design and Graphics,2016,28(6):855-868.
[37]MUR-ARTAL R,TARDOS J D.ORB-SLAM2:An Open-Source Slam System for Monocular,Stereo and RGB-D Came-ras[J].IEEE Transactions on Robotics,2017,33(5):1255-1262.
[38]ZHANG Y,LI H S,MA L,et al.Research on real-time positioning of underwater robot based on ORB-SLAM2 algorithm[J].Bulletin of Surveying and Mapping,2019(12):1-7.
[39]LU J W,WANG Y L.Construction of real-time grid map based on ORB-SLAM2[J].Application Research of Computers,2019,36(10):3124-3131.
[40]HADDADI S J,CASTELAN E B.Visual-Inertial Fusionfor Indoor Autonomous Navigation of a Quadrotor Using ORB-SLAM[C]//2018 Latin American Robotic Symposium,2018 Brazilian Symposium on Robotics(SBR) and 2018 Workshop on Robotics in Education(WRE).2018.
[41]SANTOS M,SOTO O,BUSTAMANTE V P.ORB-SLAMBased Active Disturbance Rejection Control for Quadrotor Autonomous Flight[C]//2018 XX Congreso Mexicano de Robótica(COMRob).2018.
[42]FORSTER C,PIZZOLI M,SCARAMUZZA D.SVO:Fast semi-direct monocular visual odometry[C]//IEEE International Conference on Robotics and Automation.IEEE,2014:15-22.
[43]XIAO Y,RUAN X G,ZHU X Q,et al.A Micro-UAV Monocular Vision SVO/INS Integrated Navigation Method[J].Journal of Chinese Inertial Technology,2019,27(2):211-219.
[44]MENG Y,WANG W,HAN H,et al.A visual/inertial integra-ted landing guidance method for UAV landing on the ship[J].Aerospace Science and Technology,2019,85:474-480.
[45]FORSTER C,GASSNER M,WERLBERGER M,et al.SVO:Semi-Direct Visual Odometry for Monocular and Multi-Camera Systems[J].IEEE Transactions on Robotics and Automation,2017,33(2):249-265.
[46]HUANG T.Augmented reality system based on monocularvisual odometer[D].Guangzhou:South China University of Technology,2018.
[47]LI X N,XU Z Y,ZHANG Y H.Determination of weight factors for multi-sensor data fusion[J].Journal of Spacecraft TT&C Technology,2005,24(1):65-67.
[48]AYABAKAN T,KERESTECIOGLU F.Indoor positioningusing federated Kalman Filter[C]//26th Signal Processing and Communications Applications Conference(SIU).2018.
[49]KAYA S B,ALKAR A Z.Indoor localization and tracking bymulti sensor fusion in Kalman filter[C]//26th Signal Processing and Communications Applications Conference(SIU).2018.
[50]CHEN X L,WANG J L,SUN L,et al.A Method of Date Fusion for Multi-sensor Based on Bayesian Estimation[J].Journal of Electronic Measurement and Instrument,2009.
[51]ZHANG P,DONG W H,GAO D D.An Optimal Method of Data Fusion for Multi-Sensors Based on Bayesian Estimation[J].Chinese Journal of Sensors and Actuators,2014,27(5):643-648.
[52]KE L H.Research and Implementation of SLAM Based on Deep Learning[D].Xi’an:Xi’an Polytechnic University,2019.
[53]LI S P,ZHANG T.Overview of the application of deep learning in visual SLAM[J].Space Control Technology and Application,2019,45(2):1-10.
[54]KONDA K,MEMISEVIC R.Learning visual odometry with a convolutional network[C]//Proceedings of the 10th International Conference on Computer Vision Theory and Applications.Lisbon,Portugal:SCITCC Press,2015:486-490.
[55]COSTANTE G,MANCINI M,VALIGI P,et al.Exploring representation learning with CNNs for frame-to-frame ego-motion estimation[J].IEEE Robotics and Automation Letters,2016,1(1):18-25.
[56]HE Y L,CHEN J T,ZENG B.Fast closed loop detection me-thod based on simplification convolutional neural network[J].Computer Engineering,2018,44(6):182-187.
[57]YI H,HONG Z,ZHOU S.BoCNF:Efficient image matchingwith bag of Conv-Net features for scalable and robust visual place recognition[J].Autonomous Robots (S0929-5593),2017,42(9):1-17.
[58]HOU Y,ZHANG H,ZHOU S L.Convolutional neural network based on image representation for visual loop closure detection[C]//IEEE International Conference on Information and Automation.Piscataway,USA:IEEE,2015:2238-2245.
[59]SUNDERHAUF N,SHIRAZI S,DAYOUB F,et al.On the per-
formance of Conv-Net features for place recognition[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,USA:IEEE,2015:4297-4304.
[60]MERRILL N,HUANG G.CALC2.0:Combining Appearance,Semantic and Geometric Information for Robust and Efficient Visual Loop Closure[C]//2019 IEEE/RSJInternational Confe-rence on Intelligent Robots and Systems(IROS).2019.
[61]LUO S X,ZHANG S J.Research on Closed Loop DetectionAlgorithm Based on Deep Learning[J].Computer and Digital Engineering,2019,47(3):494-502.
[62]GAO X,ZHANG T.Unsupervised learning to detect loops using deep neural networks for visual SLAM system[J].Autonomous Robots,2017,41(1):1-18.
[63]VASUDEVAN S,GACHTER S,NGUYEN V,et al.Cogni-tive maps for mobile robots-an object based approach[J].Robo-tics and Automatic Systems,2007,55(5):359-371.
[64]YAO E L,ZHANG H X,SONG H T,et al.Robust SLAM algorithm based on semantic information and edge consistency[J].Robot,2019,41(6):751-760.
[65]SUNDERHAUF N,PHAM T T,LATIF Y,et al.MeaningfulMaps with Object-Oriented Semantic Mapping[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).2017.
[66]MA L,STUCKLER J,KARL C,et al.Multi-View Deep Lear-ning for Consistent Semantic Mapping with RGB-D Cameras[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).2017.

相关文章 15

[1]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2]	邵子灏, 杨世宇, 马国杰. 室内信息服务的基础——低成本定位技术研究综述 Foundation of Indoor Information Services:A Survey of Low-cost Localization Techniques 计算机科学, 2022, 49(9): 228-235. https://doi.org/10.11896/jsjkx.210900260
[3]	唐清华, 王玫, 唐超尘, 刘鑫, 梁雯. 基于M2M相遇区的PDR室内定位方法 PDR Indoor Positioning Method Based on M2M Encounter Region 计算机科学, 2022, 49(9): 283-287. https://doi.org/10.11896/jsjkx.210800270
[4]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[5]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[6]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[7]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[8]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[9]	杨文坤, 原晓佩, 陈小锋, 郭睿. 三维激光雷达点云空间多特征分割 Spatial Multi-feature Segmentation of 3D Lidar Point Cloud 计算机科学, 2022, 49(8): 143-149. https://doi.org/10.11896/jsjkx.210300275
[10]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[11]	侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[12]	周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[13]	苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[14]	胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[15]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed