摘要
基于视觉利用移动机器人进行运动目标跟踪,该文提出一种基于二自由度云台和RGB-D相机的运动目标视觉跟踪及移动机器人路径实时规划、跟踪方法。该方法利用核相关滤波算法在图像中实时追踪目标,控制二自由度云台使深度相机实时对准目标,并根据深度相机得到目标的深度信息,利用坐标转换得到目标相对于机器人的位置信息;其后移动机器人根据目标的位置信息,基于五次多项式进行路径规划;最后采用李雅普诺夫控制律对移动机器人进行轨迹跟踪控制,使得机器人能够平稳地跟踪目标运动。该算法在阿克曼移动机器人上进行了实验,实验结果验证了算法的有效性和实时性。
The mobile robot is used to track the moving target based on vision,a method of visual tracking of moving targets and real-time path planning and tracking of mobile robots based on two-degree-of-freedom pan-tilt and RGB-D camera is proposed.This method uses the kernel correlation filter algorithm to track the target in the image in real time,and controls the two-degree-of-freedom pan-tilt to align the depth camera with the target in real time.The depth information of the target is obtained by the depth camera,and the position information of the target relative to the robot is obtained by coordinate transformation.Then the mobile robot makes path planning based on quintic polynomial according to the position information of target.Finally,Lyapunov control law is used to track the trajectory of mobile robot,so that the robot can follow the target smoothly.The algorithm is verified on Ackerman mobile robot,and the experimental results show that the algorithm is effective and real-time.
作者
钱东海
孙嘉俊
伏子帅
赵伟
QIAN Donghai;SUN Jiajun;FU Zishuai;ZHAO Wei(School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 201900,China)
出处
《自动化与仪表》
2023年第6期45-50,共6页
Automation & Instrumentation
