High-Efficient Global Localization Method of Mobile Robots Based on Feature Heat Map
YANG Zitong1, WANG Shuting1, MENG Jie1, JIANG Liquan1, XIE Yuanlong1,2
1. School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; 2. Guangdong Intelligent Robotics Institute, Dongguan 523000, China
Abstract:To solve the large-search-space and low-efficiency problems of traditional global localization algorithms in the large-scale scene, a high-efficient global localization method is proposed for mobile robots on the basis of the feature heat map. Firstly, the point/line information of the environmental grid map is extracted by combining the ray casting and point/line feature detection algorithms. Meanwhile, a robust processing strategy considering random errors is formulated, to construct the feature heat map with robust feature information. In addition, the similar strategy is applied to extracting the point/line feature information from real LiDAR point cloud. Moreover, the extracted feature information is matched with the feature heat map to obtain the initial search space. Finally, the maximum likelihood estimation localization and Monte Carlo localization methods are improved, thus the high-efficient global localization in the initial search space is accomplished. Verification tests are carried out in simulation scenarios and real large-scale workshops. Compared with the traditional maximum likelihood estimation localization method, the computing time is reduced by 90.37% averagely, while the success rate is 5.92 times higher averagely than the Monte Carlo localization method. Results show that the proposed method greatly reduces the localization search space and effectively improves the speed and accuracy of global localization.
[1] 曹风魁,庄严,闫飞,等.移动机器人长期自主环境适应研究进展和展望[J].自动化学报,2020,46(2):205-221.Cao F K, Zhuang Y, Yan F, et al. Long-term autonomous environment adaptation of mobile robots: State-of-the-art methods and prospects[J]. Acta Automatica Sinica, 2020, 46(2): 205-221. [2] Sprunk C, Lau B, Pfaff P, et al. An accurate and efficient navigation system for omnidirectional robots in industrial environments[J]. Autonomous Robots, 2017, 41(2): 473-493. [3] Li G, Huang Y, Zhang X L, et al. Hybrid maps enhanced loca-lization system for mobile manipulator in harsh manufacturing workshop[J]. IEEE Access, 2020, 8: 10782-10795. [4] Wang X C, Wang X L, Wilkes D M. Developments in mobile robot localization research[M]//Machine Learning-Based Natural Scene Recognition for Mobile Robot Localization in An Unknown Environment. Berlin, Germany: Springer, 2020: 11-33. [5] 董星亮,苑晶,张雪波,等.室内环境下基于图像序列拓扑关系的移动机器人全局定位[J].机器人,2019,41(1):83-94, 103.Dong X L, Yuan J, Zhang X B, et al. Mobile robot global localization based on topological relationship between image sequences in indoor environments[J]. Robot, 2019, 41(1): 83-94,103. [6] Pandey A, Pandey S, Parhi D R. Mobile robot navigation and obstacle avoidance techniques: A review[J]. International Robotics and Automation Journal, 2017, 2(3): 96-105. [7] Merhej J, Demerjian J, Fares K, et al. Geolocalization in smart environment[C]//Proceedings of the 8th International Conference on Sensor Networks. Setubal, Portugal: SciTePress, 2019: 108-115. [8] Pierlot V, Droogenbroeck M V. BeAMS: A beacon-based angle measurement sensor for mobile robot positioning[J]. IEEE Transactions on Robotics, 2014, 30(3): 533-549. [9] 唐恒博,陈卫东,王景川,等.高精度高鲁棒性的轨道机器人全局定位方法[J].机器人,2013,35(5):623-629.Tang H B, Chen W D, Wang J C, et al. High-precision and high-robustness global localization for rail robots[J]. Robot, 2013, 35(5): 623-629. [10] Zhang J, Han G J, Sun N, et al. Path-loss-based fingerprint localization approach for location-based services in indoor environments[J]. IEEE Access, 2017, 5: 13756-13769. [11] Gao H M, Zhang X B, Yuan J, et al. A novel global localization approach based on structural unit encoding and multiple hypothesis tracking[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(11): 4427-4442. [12] Feng S, Wu C D, Zhang Y Z, et al. Grid-based improved maxi-mum likelihood estimation for dynamic localization of mobile robots[J]. International Journal of Distributed Sensor Networks, 2014, 10(3). DOI: 10.1155/2014/271547. [13] Naseer T, Suger B, Ruhnke M, et al. Vision-based Markov loca-lization for long-term autonomy[J]. Robotics and Autonomous Systems, 2017, 89: 147-157. [14] 李海丰,胡遵河,陈新伟.PLP-SLAM:基于点、线、面特征融合的视觉 SLAM 方法[J].机器人,2017,39(2):214-220.Li H F, Hu Z H, Chen X W. PLP-SLAM: A visual SLAM method based on point-line-plane feature fusion[J]. Robot, 2017, 39(2): 214-220. [15] Feng J T, Ai C J, An Z, et al. A feature detection and matching algorithm based on Harris algorithm[C]//International Conference on Communications, Information System and Computer Engineering. Piscataway, USA: IEEE, 2019: 616-621. [16] Shazwani A N, Masrullizam M I, Nursabillilah M A, et al. A new approach to highway lane detection by using Hough transform technique[J]. Journal of Information and Communication Technology, 2020, 16(2): 244-260. [17] Thrun S, Burgard W, Fox D. Robust Monte Carlo localization for mobile robots[J]. Artificial Intelligence, 2001, 128(1/2): 99-141. [19] Hess W, Kohler D, Rapp H, et al. Real-time loop closure in 2D LIDAR SLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2016: 1271-1278.