Visual/Tactile sensing to monitor grasps with robot-hand for planar elastic objects

Abstract

Both tactile and visual sensing are important to solve problems of uncertainties inherent to the grasping tasks. In this paper, a hybrid approach based on combining tactile and RGBD data is proposed for control the robotic manipulation of elastic objects. The proposed method detects both interaction and lack of contact among fingertips and object. Also, this approach measures deformations to determine appropriated finger movements when the object's geometry changes in real time as a result of the deformation caused by the pressure. This approach was evaluated on a multi-fingered robot hand with tactile sensors in real experiments.