A tactile sensor based on magneto-sensitive elastomer to determine the position of an indentation

In this paper, we investigate the capabilities of a tactile sensor based on magneto-sensitive elastomers (MSEs). The main feature of the sensor is the determination of the position of indentation. The principle is based on inductance measurements of multiple planar coils and a soft magneto-sensitive layer. The proposed prototype consists of a linear array of hexagonal coils with overlapping sections. First, the results of the experiments are presented, which include a sampling of a sensor region with indentations of constant depth. Subsequently, we introduce a mathematical model based on the bell-shaped flux density distribution of a planar coil. This model consists of ellipse equations with three parameters and a polynomial fit for each parameter. Finally, solving the system of equations results in the determination of the x coordinate of the indentation.

Point Cloud Based Bin Picking: Object Recognition and Pose Estimation Using Region Growing Segmentation Algorithm

Presented paper describes experimental bin picking using Kinect sensor, region-growing algorithm, latest ROS-Industrial drivers and dual arm manipulator Motoman SDA10f.As well known if manipulation with objects of regular shapes by suction cup is required, it is sufficient to estimate only 5DoF for successful pick. In such a case simpler region growing algorithm may be used instead of complicated 3D object recognition and pose estimation techniques, resulting in shorter processing time and decrease of computational load. Experimental setup for such a scenario, manipulated objects and results using region growing segmentation algorithm are explained in detail. Video and link to open-source code of described application are provided as well.