As it has been observed in the behavior research, in reaching operation of animals, the hand performs a feedforward ballistic movement during which the vision system is watching only a target without seeing the hand simultaneously. We hypothesized that, for this, the two spaces, each of which is perceived by the eyes (eye-space) and is reached by the arm motion (arm-space) respectively, are fused into one. Human babies are supposed to gradually learn the fusion by themselves from their birth. This paper describes a self-organization of reaching operation in robots. We regarded the binocular movements as the main cue in the space perception for reaching rather than visual disparity. The eye-space as well as the arm-space is directly represented by a harmony of contractions of muscles controlling their movements. The fusion of the two spaces is obtained by a learn-by-doing manner via an interaction of the binocular and the arm movements, and is stored in a memory (CMAC) as a form of experience of these muscle contractions obtained through the interaction. During the learning process it is not necessary to know structure and parameters of robot systems at all.

The shape of articulated objects such as a human body can be simplified into a stick model which is represented by connections of several circular generalized cylinders (GCs). In this paper, we propose a new image feature called cue circles (CCs), and present a method how to obtain CCs from input images. Using CCs, the 3D motion of a human body is measured from a sequence of boundary contour image pairs, which is obtained by an active binocular sensor system. The body model used is represented by a set of cue spheres (CSs), each of which is located at ends of GCs. Stereo matching for recovering the body model is carried out by finding pairs of CCs between the pair of contour images under consideration: a CS is projected on the two image planes as its corresponding CCs.

This paper addresses the issue of recognizing 3-D shapes of objects from their 2-D contour pairs. A shape model, that is represented by a family of spheres of varying radii with their centers on its axis, is developed for the shape class of circular generalized cylinders (GCs) with a space-curved axis. Quasi-invariant property of the shape model is defined, and is used to recover the 3-D shapes of the shape class by solving the problem of stereo matching between their contour pairs. The recovered shapes are segmented into their parts and represented by a set of the parametrically describable parts and spatial relations between them, so that they may be used for recognition even under occluded environments.

This paper presents a method for reasoning volumetric shapes for robotic grasping based on a data-driven approach. The global information about position, orientation and geometrical property of objects is necessary for successful execution of the target approach and the preparation, at the early stage of grasping, rather than fine details of the shapes. A pair of occluding contours is used to extract a simplified 3D shape of circular generalized cylinders (GCs) holding the information. Based on the GC model, which is represented by a family of spheres of varying radii with their centers on its axis, the stereo matching between the contour pair is implemented using the geometrical invariance of spheres. The shapes of blobs and sticks can be simplified as spheres and the families of spheres, respectively. Compared with the range-data based method, its computation is inexpensive, directive and has unique solution. The case of multiple and overlap objects is also addressed.