双目视觉与惯导融合的移动机器人定位方法

doi:10.11947/j.AGCS.2021.20210250

测绘学报 ›› 2021, Vol. 50 ›› Issue (11): 1512-1521.doi: 10.11947/j.AGCS.2021.20210250

双目视觉与惯导融合的移动机器人定位方法

许智宾¹, 李宏伟², 张斌², 肖志远³, 邓晨¹

1. 郑州大学信息工程学院, 河南郑州 450052;
2. 郑州大学地球科学与技术学院, 河南郑州 450052;
3. 郑州大学水利科学与工程学院, 河南郑州 450001

收稿日期:2021-05-11 修回日期:2021-09-27 发布日期:2021-12-07
通讯作者: 李宏伟 E-mail:laob_811@sina.com
作者简介:许智宾(1996—),男,硕士生,研究方向为视觉SLAM。
基金资助:
中国工程科技发展战略河南研究院战略咨询研究项目（2020HENZT07）

Localization method of mobile robot based on binocular vision and inertial navigation

XU Zhibin¹, LI Hongwei², ZHANG Bin², XIAO Zhiyuan³, DENG Chen¹

1. School of Information Engineering, Zhengzhou University, Zhengzhou 450052, China;
2. School of Geoscience and Technology, Zhengzhou University, Zhengzhou 450052, China;
3. School of Water Conservancy Science and Engineering, Zhengzhou University, Zhengzhou 450001, China

Received:2021-05-11 Revised:2021-09-27 Published:2021-12-07
Supported by:
Strategic Consulting Research Project of Henan Research Institute of China Engineering Science and Technology Development Strategy (No. 2020HENZT07)

摘要/Abstract

摘要： 为了提高移动机器人的定位精度，提出一种双目视觉与惯导融合的视觉SLAM算法。在视觉SLAM前端部分，为了保持直接法计算速度快及特征法精度高的特点，提出一种融合直接法和特征法的半直接法双目视觉里程计。在后端优化阶段，将视觉数据与IMU数据相互融合，在滑动窗口中以非线性优化的方式构建误差函数，优化位姿计算精度。在EuRoc数据集中对本文提出的算法进行试验验证。结果表明，与开源的视觉惯导融合的SLAM系统OKVIS、ROVIO和VINS-Mono相比，本文系统在Machine Hall与Vicon Room两个场景中的定位精度均得到了明显的提升，同时可以保持较高的运行效率。

关键词: 同时定位与地图构建, 视觉惯导融合, 双目视觉, 特征法, 直接法

Abstract: To improve the positioning accuracy of mobile robot, a visual SLAM algorithm based on binocular vision and inertial navigation is presented. In the front part of visual SLAM, a semi-direct binocular visual odometer combining direct method with characteristic method is presented to maintain the fast calculation speed and high accuracy of direct method. In the back-end optimization stage, the visual data and IMU data are fused together, and error functions are constructed in a sliding window in a non-linear optimization way to optimize the accuracy of pose calculation. The algorithm proposed in this paper is validated in EuRoc dataset. The results show that the positioning accuracy of the SLAM system OKVIS, ROVIO and VINS-Mono is significantly improved in both Machine Hall and Vicon Room scenarios, while maintaining high operational efficiency, compared with the open source visual inertial navigation fusion SLAM system OKVIS, ROVIO and VINS-Mono.

Key words: SLAM, visual inertial navigation fusion, binocular vision, feature method, direct method

中图分类号:

P227

许智宾, 李宏伟, 张斌, 肖志远, 邓晨. 双目视觉与惯导融合的移动机器人定位方法[J]. 测绘学报, 2021, 50(11): 1512-1521.

XU Zhibin, LI Hongwei, ZHANG Bin, XIAO Zhiyuan, DENG Chen. Localization method of mobile robot based on binocular vision and inertial navigation[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1512-1521.

参考文献

[1] 权美香,朴松昊,李国.视觉SLAM综述[J].智能系统学报,2016,11(6):768-776. QUAN Meixiang, PIAO Songhao, LI Guo. An overview of visual SLAM[J].CAAI Transactions on Intelligent Systems, 2016,11(6): 768-776.
[2] 高翔,张涛,刘毅.视觉SLAM十四讲:从理论到实践[M].北京:电子工业出版社,2017. GAO Xiang, ZHANG Tao, LIU Yi. 14 Lectures on Visual SLAM: From Theory to Practice [M].Beijing: Publishing House of Electronics industry, 2017.
[3] FORSTER C, PIZZOLI M, SCARAMUZZA D. SVO: Fast semi-direct monocular visual odometry[C]//Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA). Hong Kong, China: IEEE, 2014: 15-22.
[4] 杨梦佳.基于惯导与双目视觉融合的SLAM技术研究[D].西安:西安科技大学,2020. YANG Mengjia. Research on SLAM technology based on inertial navigation and binocular vision fusion[D]. Xi’an: Xi’an University of Science and Technology,2020.
[5] 唐令. 基于半直接法的单目视觉里程计设计与实现[D].重庆:重庆大学,2018. TANG Ling. Design and implementation of semi-direct based monocular visual odometry[D]. Chongqing: Chongqing University, 2018.
[6] MUR-ARTAL R, TARDÓS J D. ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
[7] SCHLEGEL D, COLOSI M, GRISETTI G. ProSLAM: graph SLAM from a programmers perspective[C]//Proceedings of 2018 IEEE International Conference on Robotics and Automation (ICRA). Brisbane, QLD, Australia:IEEE, 2018: 3833-3840.
[8] SHINYA Sumikura, MIKIYA Shibuya, KEN Sakurada. OpenVSLAM: a versatile visual SLAM framework[C]//Proceedings of the 27th ACM International Conference on Multimedia.New York, USA:ACM:2019.
[9] 邸凯昌,万文辉,赵红颖,等.视觉SLAM技术的进展与应用[J].测绘学报,2018,47(6):770-779. DOI:10.11947/j.AGCS.2018.20170652. DI Kaichang, WAN Wenhui, ZHAO Hongying, et al. Progress and applications of visual SLAM[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 770-779. DOI:10.11947/j.AGCS.2018.20170652.
[10] ENGEL J, SCHÖPS T, CREMERS D. LSD-SLAM: large-scale direct monocular SLAM[M]//Proceedings of Computer Vision-ECCV 2014. Cham: Springer International Publishing, 2014: 834-849.
[11] ENGEL J, KOLTUN V, CREMERS D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3): 611-625.
[12] KERL C, STURM J, CREMERS D. Dense visual SLAM for RGB-D cameras[C]//Proceedings of 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Tokyo, Japan: IEEE, 2013: 2100-2106.
[13] MELBOUCI K, COLLETTE S N, GAY-BELLILE V, et al. Model based RGBD SLAM[C]//Proceedings of 2016 IEEE International Conference on Image Processing (ICIP). Phoenix, AZ, USA: IEEE, 2016: 2618-2622.
[14] 程传奇,郝向阳,李建胜, 等.基于非线性优化的单目视觉/惯性组合导航算法[J].中国惯性技术学报, 2017, 25(5): 643-649. CHENG Chuanqi, HAO Xiangyang, LI Jiansheng, et al. Monocular visual inertial integrated navigation algorithm based on nonlinear optimization[J].Journal of Chinese Inertial Technology, 2017,25(5):643-649.
[15] 李丰阳,贾学东,董明.惯性/视觉组合导航在不同应用场景的发展[J].导航定位学报,2016,4(4):30-35. LI Fengyang, JIA Xuedong, DONG Ming. Development of vision/inertial integrated navigation in different application scenarios[J]. Journal of Navigation and Positioning, 2016, 4(4): 30-35.
[16] MOURIKIS A I, ROUMELIOTIS S I. A multi-state constraint Kalman filter for vision-aided inertial navigation[C]//Proceedings of 2007 IEEE International Conference on Robotics and Automation. Rome, Italy: IEEE, 2007: 3565-3572.
[17] BLOESCH M, BURRI M, OMARI S, et al. Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback[J]. The International Journal of Robotics Research, 2017, 36(10): 1053-1072.
[18] LEUTENEGGER S, FURGALE P, RABAUD V, et al. Keyframe-based visual-inertial SLAM using nonlinear optimization[C]//Proceedings of 2013 Robotics: Science and Systems. Berlin, Germany: Science and Systems Foundation:2013.
[19] Robotics. Findings from Shanghai Jiao Tong University reveals new findings on robotics (structvio: visual-inertial odometry with structural regularity of man-made environments) [J]. Journal of Robotics & Machine Learning, 2019, 999-1013.
[20] QIN Tong, LI Peiliang,SHEN Shaojie. VINS-mono: a robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018,34(4):1004-1020.
[21] HARRIS C,STEPHENS M.A combined corner and edge detector[C]// Proceedings of 1988 Alvey Vision Conference 1988.Manchester. [S.l]:AlveyVision Club,1988.
[22] LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK: Binary Robust invariant scalable keypoints[C]//Proceedings of 2011 IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2548-2555.
[23] 李虎民. 融合直接法和特征法的单目SLAM技术研究[D]. 西安:西安电子科技大学2019. LI Humin. Research on monocular SLAM technology integrating direct method and indirect method [D].Xi’an: Xidian University,2019.
[24] 程俊廷,郭博洋,田宽.改进的LK光流法在SLAM中的应用[J].黑龙江科技大学学报, 2019, 29(6):736-740. CHENG Junting, GUO Boyang, TIAN Kuan. Application of improved LK optical flow method in SLAM[J]. Journal of Heilongjiang University of Science and Technology, 2019, 29(6): 736-740.
[25] BURRI M, NIKOLIC J, GOHL P, et al. The EuRoC micro aerial vehicle datasets[J]. The International Journal of Robotics Research, 2016, 35(10):1157-1163.

双目视觉与惯导融合的移动机器人定位方法

Localization method of mobile robot based on binocular vision and inertial navigation

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	赵玏洋, 闫利. 移动机器人SLAM位姿估计的改进四元数无迹卡尔曼滤波[J]. 测绘学报, 2022, 51(2): 212-223.
[2]	邵晓航, 吴杭彬, 刘春, 陈晨, 蔡天池, 程帆瑾. 语素关联约束的动态环境视觉定位优化[J]. 测绘学报, 2021, 50(11): 1478-1486.
[3]	李帅鑫, 李九人, 田滨, 陈龙, 王力, 李广云. 面向点云退化的隧道环境的无人车激光SLAM方法[J]. 测绘学报, 2021, 50(11): 1487-1499.
[4]	孙喜亮, 关宏灿, 苏艳军, 徐光彩, 郭庆华. 面向高精度城市测绘的激光紧耦合SLAM方法[J]. 测绘学报, 2021, 50(11): 1585-1593.
[5]	乌萌, 郝金明, 付浩, 高扬, 张辉. 利用解耦光流运动场模型的双目视觉里程计位姿优化方法[J]. 测绘学报, 2019, 48(4): 460-472.