Search

The intersection workspace of multi-finger hands means the overlapping workspace in 3D Euclidean space where several fingertips can reach together, and is very valuable for grasp space planning, motion control and mechanical design for multi-finger hands. But, the intersection workspaces usually have sophisticated forms, which are really hard for robotic experts to image them. We present a general approach to visualize and analyze the intersection workspace of multi-finger hands. We firstly deduce the displacement equation of the fingertip, then generate 3D workspace of the fingertip and lastly obtain the intersection workspace of the multi-finger hands. This approach can visualize intersection workspaces with integrated forms and contours, and analyze the volume of the intersection workspaces. The vivid form and volume analysis of intersection workspaces are useful for robotic experts to accurately and intuitionally understand the fingertip motion ranges, plan the motion routes of fingers and avoid the motion collision among fingers.

This paper introduces a prototype system of the tactile perception of digital images. The prototype system is comprised of several models, which include automatic image segmentation, texture shape recovery, multi-points interaction, real-time image deformation, and texture tactile rendering. For a common digit image, the prototype system in some extent can automatically recover the texture tactile information from its pixel information.

This paper explores new approaches to recognize Chinese characters in images through touch sense. We extract the gradient image fused with brightness and chrominance information by the flow-based Gauss difference algorithm, and use the edge tangential flow method to smooth image contour, to obtain smooth character contours with significant edge features. Then, we use a tactile generation algorithm with five mechanical elements to generate stable and continuous tactile information based on the normal vector of triangular patches of the surface. To verify the feasibility and effectiveness of the proposed methods, we developed a Chinese character tactile sensing system. Experiments show that Chinese characters in images can be recognized by touch sense with higher recognition accuracy rate.