基于ROS的惯性和视觉里程计的机器人室内定位
|
摘要
高精度定位是室内移动机器人的基础,针对视觉里程计在室内定位中存在的精度与累计误差的问题,提出基于ORB-SLAM2与IMU的VIORB-SLAM2视觉惯性组合定位方法,首先建立视觉里程计与机器人的坐标系联系。然后利用惯性传感器构建机器人运动预测模型,基于Kinect使用ORB-SLAM2输出视觉里程计作为机器人位姿更新,通过扩展卡尔曼滤波器对视觉里程计与IMU输出的位姿进行最优估计。设计了硬件和软件平台对提出的方法进行实验。实验表明该方法优于单独使用传统的轮式里程计与视觉里程计,有效提高了机器人移动过程中的定位精度,减少误差累积。
High-precision positioning is the basis of indoor mobile robot. For the accuracy and cumulative error of visual odometer in indoor positioning, the VIORB-SLAM2 visual inertial combined positioning method based on ORB-SLAM2 and IMU is proposed. Firstly, the visual odometer is established. The coordinate system of the robot is linked. Then the inertial sensor is used to construct the robot motion prediction model. Based on Kinect, the ORB-SLAM2 output visual odometer is used as the robot pose update, and the pose of the visual odometer and IMU output is optimally estimated by the extended Kalman filter. The hardware and software platform was designed to experiment with the proposed method. Experiments show that this method is better than the traditional wheel odometer and visual odometer alone, which effectively improves the positioning accuracy and reduces the error accumulation during the robot movement.
High-precision positioning is the basis of indoor mobile robot. For the accuracy and cumulative error of visual odometer in indoor positioning, the VIORB-SLAM2 visual inertial combined positioning method based on ORB-SLAM2 and IMU is proposed. Firstly, the visual odometer is established. The coordinate system of the robot is linked. Then the inertial sensor is used to construct the robot motion prediction model. Based on Kinect, the ORB-SLAM2 output visual odometer is used as the robot pose update, and the pose of the visual odometer and IMU output is optimally estimated by the extended Kalman filter. The hardware and software platform was designed to experiment with the proposed method. Experiments show that this method is better than the traditional wheel odometer and visual odometer alone, which effectively improves the positioning accuracy and reduces the error accumulation during the robot movement.
引文
[1] 夏凌楠,张波,王营冠,等.基于惯性传感器和视觉里程计的机器人定位[J].仪器仪表学报,2013,34(1):166-172.
[2] Endres F,Hess J,Sturm J,et al.3-D Mapping With an RGB-D Camera[J].IEEE Transactions on Robotics,2017,30(1):177-187.
[3] Labbé M,Michaud F.Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation[J].IEEE Transactions on Robotics,2013,29(3):734-745.
[4] Hornung A,Kai M W,Bennewitz M,et al.OctoMap:an efficient probabilistic 3D mapping framework based on octrees[J].Autonomous Robots,2013,34(3):189-206.
[5] 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.
[6] Mur-Artal Raul,Juan D Tardós.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] 付梦印,吕宪伟,刘彤,等.基于 RGB-D 数据的实时 SLAM 算法[J].机器人,2015,37(6):683-692.
[8] 韩晓东,刘冬,丛明.基于ORB特征和里程计信息的机器人视觉导航[J].组合机床与自动化加工技术,2017(1):109-111.
[9] Gui J,Gu D,Wang S,et al.A review of visual inertial odometry from filtering and optimisation perspectives[J].Advanced Robotics,2015,29(20):1289-1301.
[10] Falquez J M,Kasper M,Sibley G.Inertial aided dense & semi-dense methods for robust direct visual odometry[C]// Ieee/rsj International Conference on Intelligent Robots and Systems,IEEE,2016:3601-3607.
[11] Weiss S,Achtelik M W,Lynen S,et al.Real-time onboard visual-inertial state estimation and self-calibration of mavs in unknown environments[C]//Robotics and Automation (ICRA),2012 IEEE International Conference on IEEE,2012:957-964.
[2] Endres F,Hess J,Sturm J,et al.3-D Mapping With an RGB-D Camera[J].IEEE Transactions on Robotics,2017,30(1):177-187.
[3] Labbé M,Michaud F.Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation[J].IEEE Transactions on Robotics,2013,29(3):734-745.
[4] Hornung A,Kai M W,Bennewitz M,et al.OctoMap:an efficient probabilistic 3D mapping framework based on octrees[J].Autonomous Robots,2013,34(3):189-206.
[5] 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.
[6] Mur-Artal Raul,Juan D Tardós.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] 付梦印,吕宪伟,刘彤,等.基于 RGB-D 数据的实时 SLAM 算法[J].机器人,2015,37(6):683-692.
[8] 韩晓东,刘冬,丛明.基于ORB特征和里程计信息的机器人视觉导航[J].组合机床与自动化加工技术,2017(1):109-111.
[9] Gui J,Gu D,Wang S,et al.A review of visual inertial odometry from filtering and optimisation perspectives[J].Advanced Robotics,2015,29(20):1289-1301.
[10] Falquez J M,Kasper M,Sibley G.Inertial aided dense & semi-dense methods for robust direct visual odometry[C]// Ieee/rsj International Conference on Intelligent Robots and Systems,IEEE,2016:3601-3607.
[11] Weiss S,Achtelik M W,Lynen S,et al.Real-time onboard visual-inertial state estimation and self-calibration of mavs in unknown environments[C]//Robotics and Automation (ICRA),2012 IEEE International Conference on IEEE,2012:957-964.