Abstract A vision-guided grasping system for Phalaenopsis tissue culture plantlets (PTCPs) was developed and tested. In manually transplanting Phalaenopsis plantlets, the plantlet is usually grasped at the root or the stem since the leaf is fragile and is easily damaged by the gripper. An image-processing algorithm for locating a grasping point was employed to determine a suitable grasping point on the roots. A binocular stereovision algorithm was applied to compute the 3D coordinates of the grasping point. Furthermore, a grasping device with a gripper suitable for grasping the PTCP plantlet was developed and tested. Finally, the binocular vision locating algorithm was then integrated with the robotic gripper in order to construct an automatic PTCP grasping system. The experimental results indicated that the automatic grasping system had a success rate of 78.2% in grasping the plantlets in an appropriate position.