基于最小回环检测的多车协同SLAM框架
Multi-Vehicle Collaborative SLAM Framework for Minimum Loop Detection
- 电子学报 2021年49卷第11期 页码：2241-2250
- 作者机构：
1.中山大学计算机学院，广东广州 510006
2.中山大学深圳研究院，广东深圳 518057
- 作者简介：
[ "李博洋 男,1994年5月生于辽宁鞍山,现为中山大学计算机学院博士研究生,研究方向为三维环境感知.E-mail:liby3@mail2.sysu.edu.cn" ]
[ "刘思健 男,1993年6月生于广东湛江,现为中山大学计算机学院硕士研究生,研究方向为多机器人协同SLAM.E-mail:liusj37@mail2.sysu.edu.cn" ]
[ "崔明月 男,1992年11月生于山东淄博,现为中山大学计算机学院博士研究生，研究方向为智能机器人与边缘计算.E-mail:cuimy@mail2.sysu.edu.cn" ]
[ "赵治豪 男,1996年3月生于河南驻马店,现为中山大学深圳研究院硕士研究生,研究方向为智能机器人.E-mail:zhaozhh25@mail2.sysu.edu.cn" ]
[ "黄 凯（通信作者） 男,1977年10月生于广西梧州，现为中山大学计算机学院教授,博士生导师,研究方向为无人系统与智能机器人.E-mail:huangk36@mail.sysu.edu.cn" ]
- 基金信息：广州市科技计划(202007050004);深圳市基础研究(JCYJ20180507182508857);国家重点研发计划(2018YFB1802400)
DOI：10.12263/DZXB.20200951
中图分类号： TP391收稿：2020-08-31，
修回：2021-05-13，
纸质出版：2021-11-25
- 稿件说明：
移动端阅览
李博洋,刘思健,崔明月等.基于最小回环检测的多车协同SLAM框架[J].电子学报,2021,49(11):2241-2250.
LI Bo-yang,LIU Si-jian,CUI Ming-yue,et al.Multi-Vehicle Collaborative SLAM Framework for Minimum Loop Detection[J].ACTA ELECTRONICA SINICA,2021,49(11):2241-2250.
李博洋,刘思健,崔明月等.基于最小回环检测的多车协同SLAM框架[J].电子学报,2021,49(11):2241-2250. DOI： 10.12263/DZXB.20200951.
LI Bo-yang,LIU Si-jian,CUI Ming-yue,et al.Multi-Vehicle Collaborative SLAM Framework for Minimum Loop Detection[J].ACTA ELECTRONICA SINICA,2021,49(11):2241-2250. DOI： 10.12263/DZXB.20200951.
摘要
为了提升自动驾驶车辆的感知效率和准确率，解决协同感知算法中对协同条件的限制和多源数据融合等问题，本文引入基于激光雷达的即时定位与建图(Simultaneous Localization and Mapping
SLAM)算法，提出面向自动驾驶的多车协同SLAM框架.首先，车辆运行单车SLAM，构建本地约束并共享地图和位姿数据.同时车辆接收并处理其他车的数据，若其他车辆与本车已建立坐标系转换关系则直接完成数据融合，否则基于重叠区域相似点云配准解算多车坐标系转换关系.采用图的连通分支和生成森林理论跟踪数据融合情况并构建多车回环约束，基于通用图优化(General Graph Optimization
G2O)理论对全局地图优化.真实场景与KITTI数据集的实验结果表明，本文的框架无需构建包含所有车辆相对位姿的全局坐标系或满足多车相遇等约束条件，即可实现多车协同SLAM，并在SLAM的效率和准确率等指标上具有优势.
Abstract
In order to improve the perception efficiency and accuracy of autonomous driving vehicles
and to solve the limitations which correspond to the conditions and the multi-source data fusion
this paper advocates a cooperative SLAM(Simultaneous Localization and Mapping) framework for autonomous driving. Firstly
each vehicle runs single SLAM algorithm
builds the local constraints and shares the map and pose. Meanwhile
each vehicle receives and handles data from others. If the coordinate relationship has been established
the coming data is directly fused. Otherwise
the relationship is computed based on the point clouds registration in overlapping areas. The connection components and spawn forest are adopted to track and build the multi-vehicle loop constraint. General Graph Optimization algorithm (G2O) is used to optimize the global map. Experiments based on real world and KITTI dataset show that our framework outperforms relevant SLAM systems
relaxing the conditions of providing relative poses in initial stage and vehicles encountering.
关键词
Keywords
references
Deschaud J E . IMLS-SLAM: Scan-to-model matching based on 3D data [A]. 2018 IEEE International Conference on Robotics and Automation [C]. Australia : IEEE , 2018 . 2480 - 2485 .
Park C , Moghadam P , Kim S , et al . Elastic LiDAR fusion: Dense map-centric continuous-time SLAM [A]. 2018 IEEE International Conference on Robotics and Automation [C]. Australia : IEEE , 2018 . 1206 - 1213 .
弋英民 , 刘丁 . 有色过程噪声下的轮式机器人同步定位与地图构建 [J]. 电子学报 , 2010 , 38 ( 6 ): 1339 - 1343 .
Yi Y M , Liu D . Colored-state-noise simultaneous localization and map building for wheel robots [J]. Acta Electronica Sinica , 2010 , 38 ( 6 ): 1339 - 1343 . (in Chinese)
Choudhary S , Carlone L , Nieto C , et al . Distributed trajectory estimation with privacy and communication constraints: A two-stage distributed Gauss-Seidel approach [A]. 2016 IEEE International Conference on Robotics and Automation [C]. Sweden : IEEE , 2016 . 5261 - 5268 .
Dabeer O , Ding W , Gowaiker R , et al . An end-to-end system for crowdsourced 3D maps for autonomous vehicles: The mapping component [A]. 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems [C]. Canada : IEEE , 2017 . 634 - 641 .
Andre T , Neuhold D , Bettstetter C . Coordinated multi-robot exploration: Out of the box packages for ROS [A]. 2014 IEEE Globecom Workshops [C]. Austin, USA : IEEE , 2014 . 1457 - 1462 .
Cunningham A , Paluri M , Dellaert F . DDF-SAM: fully distributed slam using constrained factor graphs [A]. 2010 IEEE International Conference on Intelligent Robots and Systems [C]. Taipei, China : IEEE , 2010 . 3025 - 3030 .
Nieto-Granda C , Rogers J G III , Christensen H I . Coordination strategies for multi-robot exploration and mapping [J]. The International Journal of Robotics Research , 2014 , 33 ( 4 ): 519 - 533 .
Zhe X Y , Li B Y , Zhang X Y , et al . Online cooperative 3d mapping for autonomous driving [A]. 2018 IEEE Intelligent Vehicles Symposium [C]. Changshu, China : IEEE , 2018 . 256 - 261 .
Zhang J , Singh S . Loam: lidar odometry and mapping in real-time [EB/OL]. http://www.roboticsproceedings.org/rss10/p07.pdf 2019.11.10 http://www.roboticsproceedings.org/rss10/p07.pdf2019.11.10 .
Shan T X , Englot B . LeGO-LOAM : lightweight and ground‑optimized lidar odometry and mapping on variable terrain[A]. 2018 IEEE International Conference on Intelligent Robots and Systems [C]. Madrid, Spain : IEEE , 2018 . 4758 - 4765 .
Khairuddin A R , Talib M S , Haron H . Review on simultaneous localization and mapping (slam) [A]. 2015 IEEE International Conference on Control System, Computing and Engineering[C] . Penang , Malaysia : IEEE , 2018 . 85 - 90 .
Sun Q X , Yuan J , Zhang X B , et al . RGB-D SLAM in indoor environments with STING-based plane feature extraction [J]. IEEE/ASME Transactions on Mechatronics , 2018 , 23 ( 3 ): 1071 - 1082 .
Sun Q X , Yuan J , Zhang X B , et al . Plane-edge-SLAM: Seamless fusion of planes and edges for SLAM in indoor environments [J]. IEEE Transactions on Automation Science and Engineering , 2021 , 18 ( 4 ): 2061 - 2075 .
梁明杰 , 闵华清 , 罗荣华 . 基于图优化的同时定位与地图创建综述 [J]. 机器人 , 2013 , 35 ( 4 ): 500 - 512 .
Liang M J , Min H Q , Luo R H . Graph-based slam: A survey [J]. Robot , 2013 , 35 ( 4 ): 500 - 512 . (in Chinese)
Grisetti G , Kümmerle R , Stachniss C , et al . A tutorial on graph-based SLAM [J]. IEEE Intelligent Transportation Systems Magazine , 2010 , 2 ( 4 ): 31 - 43 .
陈凤东 , 洪炳镕 . 基于特征地图的移动机器人全局定位与自主泊位方法 [J]. 电子学报 , 2010 , 38 ( 6 ): 1256 - 1261 .
Chen F D , Hong B R . A global localization and self-docking method for mobile robot based on feature map [J]. Acta Electronica Sinica , 2010 , 38 ( 6 ): 1256 - 1261 . (in Chinese)
石杏喜 , 赵春霞 , 郭剑辉 . 基于PF/CUKF/EKF的移动机器人SLAM框架算法 [J]. 电子学报 , 2009 , 37 ( 8 ): 1865 - 1868 .
Shi X X , Zhao C X , Guo J H . The framework algorithm for mobile robot simultaneous localization and mapping based on PF/CUKF/EKF [J]. Acta Electronica Sinica , 2009 , 37 ( 8 ): 1865 - 1868 . (in Chinese)
Olson E , Leonard J , Teller S . Fast iterative alignment of pose graphs with poor initial estimates [A]. 2006 IEEE International Conference on Robotics and Automation [C]. Orlando, USA : IEEE , 2006 . 2262 - 2269 .
Grisetti G , Kümmerle R , Stachniss C , et al . Hierarchical optimization on manifolds for online 2d and 3d mapping [A]. 2010 IEEE International Conference on Robotics and Automation [C]. Anchorage, USA : IEEE , 2010 . 273 - 278 .
Reid S , et al . Coordination for multi-robot exploration and mapping [A]. Proceedings of the 17th National Conference on Artificial Intelligence and 12th Conference on Innovative Applications of Artificial Intelligence [C]. Austin, USA : ACM , 2000 . 852 - 858 .
Zhang Y C , Chen L , XuanYuan Z , et al . Three-dimensional cooperative mapping for connected and automated vehicles [J]. IEEE Transactions on Industrial Electronics , 2020 , 67 ( 8 ): 6649 - 6658 .
Indelman V , Nelson E , Michael N , et al . Multi-robot pose graph localization and data association from unknown initial relative poses via expectation maximization [A]. 2014 IEEE International Conference on Robotics and Automation [C]. Hong Kong, China : IEEE , 2014 . 593 - 600 .
Riazuelo L , Civera J , Montiel J M M . C2TAM: A cloud framework for cooperative tracking and mapping [J]. Robotics and Autonomous Systems , 2014 , 62 ( 4 ): 401 - 413 .
Aragues R , Carlone L , Calafiore G , et al . Multi-agent localization from noisy relative pose measurements [A]. 2011 IEEE International Conference on Robotics and Automation [C]. Shanghai, China : IEEE , 2011 . 364 - 369 .
Wen J , Zhang X B , Gao H M , et al . CAE-RLSM: Consistent and efficient redundant line segment merging for online feature map building [J]. IEEE Transactions on Instrumentation and Measurement , 2020 , 69 ( 7 ): 4222 - 4237 .
Thrun S . A probabilistic on-line mapping algorithm for teams of mobile robots [J]. The International Journal of Robotics Research , 2001 , 20 ( 5 ): 335 - 363 .
Cunningham A , Indelman V , Dellaert F . DDF-SAM 2.0: Consistent distributed smoothing and mapping [A]. 2013 IEEE International Conference on Robotics and Automation [C]. Karlsruhe, Germany : IEEE , 2013 . 5220 - 5227 .
高洪波 , 张新钰 , 张天雷 , 等 . 基于云模型的智能驾驶车辆变粒度测评研究 [J]. 电子学报 , 2016 , 44 ( 2 ): 365 - 373 .
Gao H B , Zhang X Y , Zhang T L , et al . Research of intelligent vehicle variable granularity evaluation based on cloud model [J]. Acta Electronica Sinica , 2016 , 44 ( 2 ): 365v373 . (in Chinese)
Geiger A , Lenz P , Urtasun R . Are we ready for autonomous driving? The KITTI vision benchmark suite [A]. 2012 IEEE International Conference on Computer Vision and Pattern Recognition [C]. Providence, USA : IEEE , 2012 . 3354 - 3361 .
0
浏览量
15
下载量
7
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies