王泽华, 梁冬泰, 梁丹, 章家成, 刘华杰. 基于惯性/磁力传感器与单目视觉融合的SLAM方法[J]. 机器人, 2018, 40(6): 933-941.DOI: 10.13973/j.cnki.robot.170683.
WANG Zehua, LIANG Dongtai, LIANG Dan, ZHANG Jiacheng, LIU Huajie. A SLAM Method Based on Inertial/Magnetic Sensors and Monocular Vision Fusion. ROBOT, 2018, 40(6): 933-941. DOI: 10.13973/j.cnki.robot.170683.
摘要针对单目视觉SLAM(同时定位与地图构建)算法没有尺度信息以及在相机移动过快时无法使用的问题,提出了一种IMU(惯性测量单元)!!/磁力传感器与单目视觉融合的SLAM方法.首先,提出了一种模糊自适应的九轴姿态融合算法,对IMU的航向角进行高精度估计.然后,采用单目ORB-SLAM2(oriented FAST and rotated BRIEF SLAM2)算法,通过IMU估计其尺度因子,并对其输出的位姿信息进行尺度转换.最后,采用松耦合方式,对IMU估计的位姿和ORB-SLAM2算法经过尺度转换后的位姿,进行卡尔曼滤波融合.在公开数据集EuRoC上进行了测试,测试结果表明本文方法总的位置均方根误差为5.73 cm.为了进一步在实际环境中验证,设计了全向移动平台,以平台上激光雷达所测的位姿数据为基准,测试结果表明本文方法的旋转角度误差小于5°,总的位置均方根误差为9.76 cm.
Abstract:To solve the problem that the monocular vision SLAM (simultaneous localization and mapping) algorithm lacks the scale information and can't be used when the camera moves too fast, a SLAM method based on IMU (inertial measurement unit)/magnetic sensor and monocular vision fusion is proposed. Firstly, a fuzzy adaptive 9-axis attitude fusion algorithm is proposed for estimating the heading angle of IMU accurately. Then, a monocular ORB-SLAM2 (oriented FAST and rotated BRIEF SLAM2) algorithm is used, its scale factor is calculated by IMU, and scale transformation of its output pose information is performed. Finally, the loosely coupled method is adopted to fuse the poses of IMU and ORB-SLAM2 algorithm after scale transformation by Kalman filter. The experiments are carried out on a public dataset EuRoC, and the results show that the total root mean square error of the method is 5.73 cm. For further verification in the actual environment, an omnidirectional mobile platform is designed, and the test results show that the rotation angle error of the method is less than 5° and the total position RMSE is 9.76 cm compared with the pose data measurements from the lidar.
[1] Davison A J, Reid I D, Molton N D, et al. MonoSLAM:Real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):1052-1067.
[2] Klein G, Murray D. Parallel tracking and mapping for smallAR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2007.
[3] Mur-Artal R, Montiel J M M, Tardós J D. ORB-SLAM:A versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2017, 31(5):1147-1163.
[4] Mur-Artal R, Tardos J D. ORB-SLAM2:An open-sourceSLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 2017, 33(5):1255-1262.
[5] Engel J, Schöps T, Cremers D. LSD-SLAM:Large-scale directmonocular SLAM[M]//Lecture Notes in Computer Science, vol.8690. Berlin, Germany:Springer, 2014:834-849.
[6] Forster C, Pizzoli M, Scaramuzza D. SVO:Fast semi-direct monocular visual odometry[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014:15-22.
[7] Qin T, Li P L, Shen S J. VINS-Mono:A robust and versatile monocular visual-inertial state estimator[EB/OL]. (2017-08-13)[2017-12-22]. https://arxiv.org/abs/1708.03852v1.
[8] Lin Y, Gao F, Qin T, et al. Autonomous aerial navigation using monocular visual-inertial fusion[J]. Journal of Field Robotics, 2018, 35(1):23-51.
[9] Mur-Artal R, Tardós J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2016, 2(2):796-803.
[10] 郑威,彭刚.基于惯性/磁力传感器的行人3维轨迹跟踪技术[J].机器人,2016,38(4):444-450.Zheng W, Peng G. 3D pedestrian trajectory tracking based on inertial/magnetic sensors[J]. Robot, 2016, 38(4):444-450.
[11] Madgwick, S. An efficient orientation filter for inertial and inertial/magnetic sensor arrays[R]. Bristol, UK:University of Bristol, 2010.
[12] 刘金琨.智能控制[M].3版.北京:电子工业出版社,2014:47-57.Liu J K. Intelligent control[M]. 3rd ed. Beijing:Publishing House of Electronics Industry, 2014:47-57.
[13] 周绍磊,吴修振,刘刚,等.一种单目视觉ORB-SLAM/INS组合导航方法[J].中国惯性技术学报,2016,24(5):633-637.Zhou S L, Wu X Z, Liu G, et al. Integrated navigation method of monocular ORB-SLAM/INS[J]. Journal of Chinese Inertial Technology, 2016, 24(5):633-637.
[14] Burri M, Nikolic J, Gohl P, et al. The EuRoC micro aerial vehicle datasets[J]. International Journal of Robotics Research, 2016, 35(10):1157-1163.
[15] Kohlbrecher S, van Stryk O, Meyer J, et al. A flexible and scalable SLAM system with full 3D motion estimation[C]//IEEE International Symposium on Safety, Security, and Rescue Robotics. Piscataway, USA:IEEE, 2011:155-160.
[16] Santos J M, Portugal D, Rocha R P. An evaluation of 2D SLAM techniques available in robot operating system[C]//IEEE International Symposium on Safety, Security, and Rescue Robotics. Piscataway, USA:IEEE, 2013.