智能空间中家庭服务机器人所需完成的主要任务是协助人完成物品的搜寻、定位与传递。而视觉伺服则是完成上述任务的有效手段。搭建了由移动机器人、机械臂、摄像头组成的家庭服务机器人视觉伺服系统,建立了此系统的运动学模型并对安装在机械臂末端执行器上的视觉系统进行了内外参数标定,通过分解世界平面的单应来获取目标物品的位姿参数,利用所获取的位姿参数设计了基于位置的视觉伺服控制律。实验结果表明,使用平面单应分解方法来设计控制律可简单有效地完成家庭物品的视觉伺服任务。
In intelligent space,the main task for home service robot is searching,positioning and delivering the targets(such as cups,medicine,books).The visual servoing method is necessarily needed to finish such tasks.The visual servoing system,which is com-posed of a mobile robot,a 4-DOF manipulator and a camera,is constructed.The kinematic model of the system,along with the calibration of the internal and external parameters of the camera mounted on the manipulator's end effector,is set up.The target's position and pose parameters,which are used to design the position based visual servoing control law,are extracted from homography decomposition method.An object handling experiment is used to validate its validity.The experimental results show that,using this method,the visual servoing tasks for home environment can be finished easily and efficiently.