计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 240400051-9.doi: 10.11896/jsjkx.240400051

• 图像处理&多媒体技术 • 上一篇    下一篇

一种融合激光与视觉的轻量级地貌地图构建方法

李雅雯1, 张波涛1,2, 仲朝亮1,2, 吕强1,2   

  1. 1 杭州电子科技大学自动化学院 杭州 310018
    2 杭州电子科技大学浙江省自主机器人系统国际联合实验室 杭州 310018
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 张波涛(billow@hdu.edu.cn)
  • 作者简介:(liyawen@hdu.edu.cn)
  • 基金资助:
    国家自然科学基金(62073108);浙江省自然科学基金(LZ23F030004);浙江省属高校基本科研业务专项资金重点项目(GK229909299001-004)

Lightweight Terrain Map Building Approach Combining Laser and Vision

LI Yawen1, ZHANG Botao1,2, ZHONG Chaoliang1,2, LYU Qiang1,2   

  1. 1 School of Automation,Hangzhou Dianzi University,Hangzhou 310018,China
    2 International Joint Research Laboratory for Autonomous Robotic Systems,Hangzhou Dianzi University,Hangzhou 310018,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:LI Yawen,born in 2000,postgraduate.Her main research interests including environment modeling and navigation for outdoor robots.
    ZHANG Botao,born in 1982,Ph.D,associate professor.His main research interests including machine vision,motion planning and control of mobile robots.
  • Supported by:
    National Natural Science Foundation of China(62073108),Natural Science Foundation of Zhejiang Province,China(LZ23F030004) and Fundamental Research Funds for the Provincial Universities of Zhejiang (GK229909299001-004).

PDF (PC)

195

摘要： 机器人在复杂环境中的工作性能与环境的交互作用息息相关,但传统的几何映射无法充分捕捉环境的细节信息。然而,现有的移动机器人的环境模型通常为二分类激光地图或小范围的低实时性语义地图,缺乏可承载多样化地貌信息的轻量级环境模型。针对该问题,文中提出了一种融合激光与视觉的轻量级地貌地图构建方法。该方法在时间和空间同步的基础上,利用改进CSPResnet的轻量级网络提取地貌的语义信息,并与点云相融合生成包含地貌信息的语义点云,以构建具有地形描述的地貌地图。同时为通过并行策略提高构图实时性,采用改进的ICP算法对点云配准进行优化,基于局部子图拼接方法构建大范围场景下的地貌地图。在实际场景中进行实验,结果表明所提方法可有效识别多种典型地貌,并在有限机载算力下构建轻量级地貌地图。

关键词: 移动机器人, 轻量级语义地图, 地貌地图, 并行地图构建

Abstract: The performance of robots in complex environments is closely related to the interaction with the environment,and traditional geometric mapping can not capture the detailed information of the enviroment adequately.To deal with the problems mentioned above,this study proposes a lightweight terrain map building approach combining laser and vision(LTMB-LV).Based on temporal and spatial synchronization,this method extracts semantic terrain information with improved CSPResnet and fuses it with point clouds to generate semantic point clouds involving terrain information,thereby building a terrain map with terrain description.Meanwhile,local subgraph stitching method based on an improved ICP for optimizing point cloud registration is employed for building terrain maps in large-scale scenarios,while a parallel method enhances real-time performance.Experimental results in real environments demonstrate that the proposed approach can efficiently detect many typical terrains and construct lightweight terrain maps with limited onboard computational power.

Key words: Mobile robots, Lightweight semantic map, Terrain map, Parallel mapping

中图分类号: 

  • TP242
[1]SOUSA Y,BASSANI H.Topological semantic mapping by consolidation of deep visual features[J].IEEE Robotics and Automation Letters,2022,7(2):4110-4117.
[2]LU J,TIAN B,SHEN H,et al.Real-time instance-aware segmentation and semantic mapping on edge devices[J].IEEE Transactions on Instrumentation and Measurement,2022,72:1-9.
[3]WU R,ZHANG X,XU X,et al.Learning predictive trackingcontrol method with Gaussian process modeling for mobile robots[J].Control Theory and Applications,2023,40(12):2236-2246.
[4]IKEUCHI A,TAKAMORI T,KOBAYASHI S,et al.Development of mobile robots for search and rescue operation systems[J].Field and Service Robotics,2006,24:519-528.
[5]HELLSTRÖM T,JOHANSSON T,RINGDAHL O.Develop-ment of an autonomous forest machine for path tracking[C]// Field and Service Robotics:Results of the 5th International Conference.Springer Berlin Heidelberg,2006:603-614.
[6]SCHENKER P,HUNTSBERGER T,PIRJANIAN P,et al.Planetary rover developments supporting mars exploration,sample return and future human-robotic colonization[J].Autonomous Robots,2003,14:103-126.
[7]CHGHAF M,RODRIGUEZ S,OUARDI A.Camera,LiDARand multi-modal SLAM systems for autonomous ground vehicles:a survey[J].Journal of Intelligent and Robotic Systems,2022,105(1):1-35.
[8]SCHILLING F,CHEN X,FOLKESSON J,et al.Geometric and visual terrain classification for autonomous mobile navigation[C]// 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).Canada:IEEE,2017:2678-2684.
[9]WIGNESS M,EUM S,ROGERS J,et al.A rugd dataset for au-tonomous navigation and visual perception in unstructured outdoor environments[C]// 2019 IEEE/RSJ International Confe-rence on Intelligent Robots and Systems(IROS).China:IEEE,2019:5000-5007.
[10]MCCORMAC J,HANDA A,DAVISON A,et al.Semanticfusion:dense 3D semantic mapping with convolutional neural networks[C]// 2017 IEEE International Conference on Robotics and automation(ICRA).Singapore:IEEE,2017:4628-4635.
[11]WILSON J,SONG J,FU Y,et al.MotionSC:data set and network for real-time semantic mapping in dynamic environments[J].IEEE Robotics and Automation Letters,2022,7(3):8439-8446.
[12]HU M,ZHANG Y,QIN C,et al.Semantic map constructionbased on deep convolutional neural network[J].ROBOT,2019,41(4):452-463.
[13]QIN T,CHEN T,CHEN Y,et al.Avp-slam:semantic visualmapping and localization for autonomous vehicles in the parking lot[C]// 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).USA:IEEE,2020:5939-5945.
[14]YANG L,WANG L.A semantic SLAM-based dense mappingapproach for large-scale dynamic outdoor environment[J].Measurement,2022,204:1-9.
[15]QI C,SU H,MO K,et al.Pointnet:deep learning on point sets for 3D classification and segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:652-660.
[16]BEHLEY J,GARBADE M,MILIOTO A,et al.Towards 3D Li-DAR-based semantic scene understanding of 3D point cloud sequences:the semantic KITTI dataset[J].The International Journal of Robotics Research,2021,40(8/9):959-967.
[17]KONG X,YANG X,ZHAI G,et al.Semantic graph based place recognition for 3D point clouds[C]// 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).USA:IEEE,2020:8216-8223.
[18]CHEN X,MILIOTO A,PALAZZOLO E,et al.Suma++:efficient lidar-based semantic slam[C]// 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).China:IEEE,2019:4530-4537.
[19]PAZ D,ZHANG H,LI Q,et al.Probabilistic semantic mapping for urban autonomous driving applications[C]// 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).USA,IEEE,2020:2059-2064.
[20]XIE J,QIAN Y,WANG B,et al.Off-load semantic terrain classification using 3D LiDAR data[C]// 2022 China Automation Congress(CAC).China:IEEE,2022:5960-5965.
[21]CHEN L,FAN L,CHEN J,et al.A full density stereo matching system based on the combination of CNNs and slanted-planes[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2017,50(2):397-408.
[22]LEE H,LEE S,CHOI M,et al.Probabilistic map merging for multi-robot RBPF-SLAM with unknown initial poses[J].Robotica,2012,30(2):205-220.
[23]LEE H,LEE K.Multi-robot SLAM using ceiling vision[C]// 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.USA,IEEE,2009:912-917.
[24]WANG K,JIA S,LI Y,et al.Research on map merging formulti-robotic system based on RTM[C]// 2012 IEEE International Conference on Information and Automation.China:IEEE,2012:156-161.
[25]ZHU J H,ZHOU Y,WANG X C,et al.Grid map merging approach based on image registration[J].Acta Automatica Sinica,2015,41(2):285-294.
[26]ZHANG Y C,CHEN L,YUAN Z X,et al.Three-dimensional cooperative mapping for connected and automated vehicles[J].IEEE Transactions on Industrial Electronics,2019,67(8):6649-6658.
[27]WU J,WANG J,WEI C.Robust map merging method for collaborative LiDAR-based SLAM using GPS sensor[C]// Journal of Physics:Conference Series.IOP Publishing,2022:1-11.
[28]SHABAN A,MENG X,LEE J,et al.Semantic terrain classification for off-road autonomous driving[C]// Conference on Robot Learning.PMLR,2022:619-629.
[29]KIDO D,FUKUDA T,YABUKI N.Assessing future landscapesusing enhanced mixed reality with semantic segmentation by deep learning[J].Advanced Engineering Informatics,2021,48:1-13.
[30]WANG S,CHEN T,LV X,et al.Forest fire detection based on lightweight yolo[C]// 2021 33rd Chinese Control and Decision Conference(CCDC).2021:1560-1565.
[31]ZHANG J,SINGH S.LOAM:lidar odometry and mapping in real-time[C]// Robotics:Science and systems.China:IEEE,2014,2(9):1-9.
[32]SHAN T,ENGLOT B,MEYERS D,et al.LIO-SAM:tightly-coupled lidar inertial odometry via smoothing and mapping[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).USA:IEEE,2020:5135-5142.
[33]CHETVERIKOV D,SVIRKO D,STEPANOV D,et al.Thetrimmed iterative closest point algorithm[C]// 2002 International Conference on Pattern Recognition.Canada:IEEE,2002,3:545-548.
[34]KUNA D,SANTHOSH N,PERUMALLA N.Preliminary ana-lysis of standalone galileo and navic in the context of positioning performance for low latitude region[J].Procedia Computer Science,2020,171:225-234.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发