基于ROS的惯性和视觉里程计的机器人室内定位

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。

Indoor Positioning by Visual-inertial Odometry Based on ROS

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.