基于改进卡尔曼滤波的移动机器人目标识别与定位研究

Research on Mobile Robot Target Recognition and Location Based by Improved Kalman Filter

针对单目移动机器人在目标识别与位置估算中深度信息丢失的问题,为提高采用激光雷达辅助距离测量的定位精确度,提出融合雷达测距信息与方位解算的改进卡尔曼滤波算法。使用YOLO网络进行目标识别,再利用基础计算机视觉标定方法获取目标方向角信息,进而利用雷达进行多次定向测距得到多个观测值;然后在目标位置解算时,根据不同观测值的距离与方位信息加权设置不同置信度,以改变卡尔曼滤波器的观测噪声与系统噪声,进而动态改进卡尔曼增益,实现具有自适应性的目标位置解算。仿真与实验结果表明:该方法相较单纯依靠雷达进行测距补充能实现更为精准的定位,具有较好的应用前景。

Aiming at the problem of depth information loss in target recognition and position estimation of monocular mobile robots,an improved Kalman filter algorithm combining radar ranging information and azimuth was proposed to improve the positioning accuracy of lidar assisted distance measurement.The YOLO network was used for target recognition,and then basic computer vision calibration methods were used to obtain target directional angle information.Radar was used for multiple directional ranging to obtain multiple observation values.Then,during the target position calculation,different confidence levels were weighted according to the distance and azimuth information of different observations to change the observation noise and system noise of the Kalman filter,and then the Kalman gain was dynamically improved to achieve adaptive target position calculation.The simulation and experimental results show that this method can achieve more accurate positioning compared to relying solely on radar for ranging supplementation,and has good application prospects.