基于视觉与IMU融合的采茶机器人位姿估计研究

Research on Tea Picking Robot’s Pose Estimation by Using Vision and IMU Fusion

为实现采茶机器人在室外复杂茶园环境中实时定位与移动轨迹跟踪,并以较低的计算代价获得较高的精度,使用双目摄像头与IMU作为传感器,采用视觉惯性里程计算法OKVIS,通过实验对比视觉里程计、松耦合的视觉惯性里程计与紧耦合的视觉惯性里程计。结果表明该算法精度较高。最终采用OKVIS算法,在室外茶园环境中验证采茶机器人的实时定位与轨迹跟踪。实验结果表明,所提方案实际运行结果良好,可以满足采茶机器人位姿估计要求。

To achieve tea picking robot's real time pose estimation and trajectory tracking in complex outdoor environment of tea garden and get higher positioning accuracy through lower calculation cost, binocular camera and IMU are used as sensors, and visual-inertial odometry algorithm OKVIS is used to estimate robot's pose. According to the experiment, visual odometry, looselycoupled visual-inertial odometry and tightly-coupled visual-inertial odometry are compared. The experiment result suggests that this algorithm has a higher accuracy. Finally, OKVIS algorithm is adopted to verify tea picking robot's real time pose estimation and trajectory tracking in outdoor environment of tea garden. The result shows that the project suggested works well and it can satisfy the requirement of tea picking robot's pose estimation.