基于无人机点云地图的地面机器人重定位方法

doi:10.16182/j.issn1004731x.joss.23-0751

摘要/Abstract

摘要：

针对无GNSS(global navigation satellite system)环境下空地协同系统中地面机器人重定位难题及其精度不足的问题，提出了一种基于三维点云地图的由粗到精的重定位算法。通过索引滤波消除高空和地面无效点云的影响，并在提取点云全局特征后引入截断最小二乘估计进行粗定位，采用体素法ICP(iterative closest point)精优化，以获得更精确的定位结果。构建了一种基于空中全局地图的地面机器人定位与自主移动框架，并通过仿真平台实验证明了该框架的可行性，验证了地面机器人重定位算法的实时性和准确性。

关键词: 地面机器人, 重定位, 无人机, 全局点云地图, 自主移动

Abstract:

In response to the challenge of relocalization in air-ground collaborative systems without the support of Global Navigation Satellite System (GNSS), and the associated issues of insufficient accuracy, a coarse-to-fine relocalization algorithm based on a three-dimensional point cloud map is proposed. The algorithm eliminates the influence of invalid point clouds from the sky and ground through index filtering, performs coarse localization by extracting global features from the point cloud and applying truncated least squares estimation, and then employs voxel-based iterative closest point (ICP) for precise optimization to obtain the more accurate localization results. A ground robot localization and autonomous navigation framework is constructed based on an aerial global map and the feasibility of the framework is validated through experiments on a simulation platform, while the real-time and accuracy of the ground robot relocalization algorithm is verified.

Key words: ground robot, relocalization, UAV, global point cloud map, autonomous navigation

中图分类号:

TP242

黄宏智,颜凯,刘昌锋等 . 基于无人机点云地图的地面机器人重定位方法[J]. 系统仿真学报, 2024, 36(10): 2444-2454.

Huang Hongzhi,Yan Kai,Liu Changfeng,et al . Ground Robot Relocation Method Based on UAV Point Cloud Map[J]. Journal of System Simulation, 2024, 36(10): 2444-2454.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

表2

表3

图11

参考文献 29

1	Butzke J, Gochev K, Holden B, et al. Planning for a Ground-air Robotic System with Collaborative Localization[C]//2016 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2016: 284-291.
2	朱新平, 瞿菁菁, 徐川. 森林火灾救援空地一体化指挥体系设计[J]. 消防科学与技术, 2022, 41(9): 1287-1290.
	Zhu Xinping, Qu Jingjing, Xu Chuan. Air-ground Integrated Command System Design for Forest Fire Rescue[J]. Fire Science and Technology, 2022, 41(9): 1287-1290.
3	Mehmood Saqib, Ahmed Shakeel, Anders Schmidt Kristensen, et al. Multi Criteria Decision Analysis (MCDA) of Unmanned Aerial Vehicles (UAVs) as a Part of Standard Response to Emergencies[C]//4th International Conference on Green Computing and Engineering Technologies. Esbjerg: Gyancity International Publishers, 2018: 116.
4	Batzdorfer S, Bobbe M, Becker M, et al. Multisensor Equipped UAV/UGV for Automated Exploration[C]//2017 International Conference on Unmanned Aerial Vehicles. Hannover: ISPRS, 2017: 33-40.
5	Mueggler Elias, Faessler Matthias, Fontana Flavio, et al. Aerial-guided Navigation of a Ground Robot Among Movable Obstacles[C]//2014 IEEE International Symposium on Safety, Security, and Rescue Robotics (2014). Piscataway: IEEE, 2014: 1-8.
6	El Houssein Chouaib Harik, Guérin François, Guinand Frédéric, et al. UAV-UGV Cooperation for Objects Transportation in an Industrial Area[C]//2015 IEEE International Conference on Industrial Technology (ICIT). Piscataway: IEEE, 2015: 547-552.
7	Heppner Georg, Roennau Arne, Dillman Ruediger. Enhancing Sensor Capabilities of Walking Robots Through Cooperative Exploration with Aerial Robots[J]. Journal of Automation, Mobile Robotics and Intelligent Systems, 2013, 7(2): 5-11.
8	马跃龙, 曹雪峰, 陈丁, 等. 一种基于点云地图的机器人室内实时重定位方法[J]. 系统仿真学报, 2017, 29(增1): 15-23, 29.
	Ma Yuelong, Cao Xuefeng, Chen Ding, et al. A Method for Real-time Relocalization of Indoor Robot with Point Cloud Map[J]. Journal of System Simulation, 2017, 29(S1): 15-23, 29.
9	He Li, Wang Xiaolong, Zhang Hong. M2DP: A Novel 3D Point Cloud Descriptor and Its Application in Loop Closure Detection[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2016: 231-237.
10	Uy M A, Lee G H. PointNetVLAD: Deep Point Cloud Based Retrieval for Large-scale Place Recognition[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4470-4479.
11	Kim Giseop, Kim Ayoung. Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2018: 4802-4809.
12	Bosse M, Zlot R. Place Recognition Using Keypoint Voting in Large 3D Lidar Datasets[C]//Proceedings of 2013 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2013: 2677-2684.
13	Gawel Abel, Cieslewski Titus, Dubé Renaud, et al. Structure-based Vision-laser Matching[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2016: 182-188.
14	Segal A V, Haehnel D, Thrun S. Generalized-ICP[EB/OL]. [2023-06-12]. .
15	Rusu R B, Cousins S. 3D Is Here: Point Cloud Library (PCL)[C]//2011 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2011: 1-4.
16	Yang Heng, Shi Jingnan, Carlone L. TEASER: Fast and Certifiable Point Cloud Registration[J]. IEEE Transactions on Robotics, 2021, 37(2): 314-333.
17	Zhou Qianyi, Park J, Koltun V. Fast Global Registration[C]//Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 766-782.
18	Yang Heng, Carlone L. A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates[EB/OL]. (2019-06-30) [2023-06-12]. .
19	Yang Heng, Antonante P, Tzoumas V, et al. Graduated Non-convexity for Robust Spatial Perception: From Non-minimal Solvers to Global Outlier Rejection[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 1127-1134.
20	Perera S, Barnes N. Maximal Cliques Based Rigid Body Motion Segmentation with a RGB-D Camera[C]//Computer Vision-ACCV 2012. Berlin: Springer Berlin Heidelberg, 2013: 120-133.
21	Koide Kenji, Yokozuka Masashi, Oishi Shuji, et al. Voxelized GICP for Fast and Accurate 3D Point Cloud Registration[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2021: 11054-11059.
22	Bai Chunge, Xiao Tao, Chen Yajie, et al. Faster-LIO: Lightweight Tightly Coupled Lidar-inertial Odometry Using Parallel Sparse Incremental Voxels[J]. IEEE Robotics and Automation Letters, 2022, 7(2): 4861-4868.
23	岳伟韬, 苏婧, 谷志珉, 等. 占据栅格地图的最佳栅格大小与地图精度[J]. 机器人, 2020, 42(2): 199-206.
	Yue Weitao, Su Jing, Gu Zhimin, et al. Best Grid Size of the Occupancy Grid Map and Its Accuracy[J]. Robot, 2020, 42(2): 199-206.
24	Hart P E, Nilsson N J, Raphael B. A Formal Basis for the Heuristic Determination of Minimum Cost Paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(2): 100-107.
25	Cao Chao, Zhu Hongbiao, Yang Fan, et al. Autonomous Exploration Development Environment and the Planning Algorithms[C]//2022 International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2022: 8921-8928.
26	Shah S, Dey D, Lovett C, et al. AirSim: High-fidelity Visual and Physical Simulation for Autonomous Vehicles[C]//Field and Service Robotics. Cham: Springer International Publishing, 2018: 621-635.
27	Hartley R, Trumpf J, Dai Yuchao, et al. Rotation Averaging[J]. International Journal of Computer Vision, 2013, 103(3): 267-305.
28	Baek Jieun, Park Junhyeok, Cho Seongjun, et al. 3D Global Localization in the Underground Mine Environment Using Mobile LiDAR Mapping and Point Cloud Registration[J]. Sensors, 2022, 22(8): 2873.
29	Zha Yongjian, Chen Ming, Lu Shenglian. Research on Point Cloud Registration of Industrial Parts Based on FGR-ICP Algorithm[J]. Journal of Physics: Conference Series, 2021, 1941(1): 012014.

场景	数据组号	局部点云组数量	重定位成功数量	成功率/%	平均距离误差/m	平均旋转误差/rad	平均耗时/s
工厂	1	73	70	95.89	0.113	0.009	14.377
	2	58	56	96.55	0.144	0.010	14.693
	3	103	100	97.09	0.112	0.011	14.587
	4	63	60	95.24	0.113	0.009	14.238
城市	1	94	93	98.94	0.109	0.008	17.753
	2	130	127	97.69	0.132	0.012	17.682
	3	89	85	95.51	0.125	0.010	17.365
	4	168	162	96.43	0.146	0.013	17.587

算法	成功率/%	平均距离误差/m	平均旋转误差/rad	平均耗时/s
本文算法	97.08	0.112	0.011 1	14.587
FPFH-RANSAC粗匹配+ICP细匹配	36.89	0.263	0.012 8	20.109
FGR粗匹配+ICP细匹配	90.29	0.108	0.009 8	32.869

高斯噪声方差/m	成功率/%	平均距离误差/m	平均旋转误差/rad	平均耗时/s
0	97.08	0.112	0.011 1	14.587
0.05	97.08	0.115	0.010 9	14.786
0.10	96.11	0.127	0.013 6	17.830
0.15	92.23	0.198	0.013 4	22.634
0.20	88.34	0.277	0.016 4	28.611

[1]	李二超, 张生辉. 基于DMOEA-APTC算法的无人机在线航迹规划[J]. 系统仿真学报, 2024, 36(9): 2086-2099.
[2]	刘斌, 兰莹, 黄文焘, 范勤勤. 融合动态窗口法的无人机动态路径规划算法[J]. 系统仿真学报, 2024, 36(8): 1843-1853.
[3]	黄志锋, 刘媛华. 基于改进哈里斯鹰和B-spline曲线的无人机路径规划研究[J]. 系统仿真学报, 2024, 36(7): 1509-1524.
[4]	王涛, 吉晓东. 混合概率信道下的全双工无人机中继轨迹优化[J]. 系统仿真学报, 2024, 36(6): 1369-1377.
[5]	高超, 黄郑, 赵轩, 王红星, 龙涛. 基于构型优选的5G集群无人机协同导航方法[J]. 系统仿真学报, 2024, 36(4): 981-990.
[6]	余翔, 邓千锐, 段思睿, 姜陈. 一种多无人机协同优先覆盖搜索算法[J]. 系统仿真学报, 2024, 36(4): 991-1000.
[7]	桂雪琪, 李春涛. 基于视野和速度引导的无人机集群避障算法[J]. 系统仿真学报, 2024, 36(3): 545-554.
[8]	李高扬, 黎向锋, 赵康, 金玉超, 易志东, 左敦稳. 全粒子推动野马优化算法的无人机三维路径规划[J]. 系统仿真学报, 2024, 36(3): 595-607.
[9]	卢元杰, 龙珊珊, 赵航, 冯国旭, 赵晓葭. 基于混合模型的异构无人机蜂群效能评估[J]. 系统仿真学报, 2024, 36(3): 700-712.
[10]	马赟, 王源, 李蒙, 王鹏, 汤艳玲. 非平面全驱动多旋翼无人机的鲁棒预测控制[J]. 系统仿真学报, 2024, 36(2): 415-422.
[11]	杨哲, 崔颖函, 郭灵犀, 李嘉鑫, 吴旭生. 融合数据仿真与深度学习算法的飞行器残骸搜寻技术[J]. 系统仿真学报, 2024, 36(10): 2238-2245.
[12]	程洁, 郑远, 李诚龙, 江波. 面向超低空物流场景的多机协同航迹规划算法[J]. 系统仿真学报, 2024, 36(1): 50-66.
[13]	焦嵩鸣, 首云锋, 白健鹏, 王祝. 变电站巡检无人机分层运动规划方法研究[J]. 系统仿真学报, 2023, 35(9): 1975-1984.
[14]	牛双诚, 晋玉强, 寇昆湖. 基于区块链的多无人机协同任务分配方法研究[J]. 系统仿真学报, 2023, 35(5): 949-956.
[15]	付玉, 张垚, 赵萌, 王绵沼, 郑江鹏, 贾晨, 陈胜勇. 基于仿真数据迁移学习的固定翼无人机检测[J]. 系统仿真学报, 2023, 35(5): 998-1007.