Yoshito Yabuta

Binocular robot vision system with shape recognition

A binocular robot vision system having an autonomously moving active viewpoint is proposed. By using this active viewpoint, the system constructs a correspondence between the images of a feature points on the right and left retinas easily and calculates the spatial coordinates of the feature points. The system incorporates a function that detects straight lines in an image. To detect lines the system uses Hough transform. The system searches a region surrounded by 4 straight lines. Then the system recognizes the region as a quadrangle. The system constructs a correspondence between the quadrangles in the right and left images. By the use of the result of the constructed correspondence, the system calculates the spatial coordinates of an object. An experimental result shows the effect of the recognition of the surface of the object and the calculation of the spatial coordinates of the object.

Vibration control of a high-speed air-bearing spindle using an active aerodynamic bearing

A novel high speed air-bearing spindle is proposed as a tool spindle for small diameter of cutting and grinding tools. The spindle vibration at high rotational speed is suppressed by an active aerodynamic bearing incorporated into the spindle. For generating aerodynamic damping force, the wedge angle on the aerodynamic bearing surface is controlled by piezoelectric actuators. By using several control tactics, the effect of the active control of the aerodynamic bearing on the spindle vibration is analyzed. Experimental result shows that the amplitude of the spindle vibration can be suppressed to be 0.1μm at the rotational speed of 50,000 min-1 (833 Hz). Final goal of the study is to suppress the amplitude of spindle vibration less than 0.1 μm at the rotational speed of 120,000 min-1 (2 kHz).

Active Aerostatic Bearings for Ultraprecision Applications

For ultraprecision applications, two types of active control restrictors for aerostatic bearings are evaluated. The first restrictor is called an aerostatically controlled restrictor (ACR), a bearing-pressure-feedback type. The change in the pressure on the bearing surface directly controls the restriction gap, and the stiffness of the aerostatic bearing with the ACR can be infinite. The second restrictor is called an active inherent restrictor (AIR), a bearing-gap-feedback type. The change in the air-gap on the bearing surface is detected by an electric sensor, and then an electric actuator controls the restriction gap. By using the AIR, infinite bearing stiffness and nanometer-order of rotational accuracy of the spindle can be realized. Positioning with subnanometer order of resolution can also be executed by an aerostatic guideway with the AIR.

Binocular Robot Vision System with Shape Recognition

A binocular robot vision system having an autonomously moving active viewpoint is proposed. By using this active viewpoint, the system constructs a correspondence between the images of a feature points on the right and left retinas easily and calculates the spatial coordinates of the feature points. The system incorporates a function that detects straight lines in an image. To detect lines the system uses Hough transform. The system searches a region surrounded by 4 straight lines. Then the system recognizes the region as a quadrangle. The system constructs a correspondence between the quadrangles in the right and left images. By the use of the result of the constructed correspondence, the system calculates the spatial coordinates of an object. An experiment shows the effect of the line detection using Hough transform, the recognition of the surface of the object and the calculation of the spatial coordinates of the object

Object detection by following saccadic movement

By using saccadic motion, human beings perform visual perception. In this paper, a function for object detection using saccadic motion is proposed. To measure distance, the proposed object detection function is built into a system with stereo vision. Saccadic motion is very important in maintaining human visual perception. In this paper, we propose a function for detecting objects based on the saccadic motion of human eyes. Experimental results show the ability of this function.

Novel Diaphragm-Control Restrictor for Precision Hydrostatic-Bearing Spindle

A novel diaphragm-control restrictor (DCR) is proposed for improving the performance of the hydrostatic-bearing spindle used in machine tools. The unique function of the proposed DCR is the wide adjustability of its restrictor characteristic. A two-step restriction system is adopted for the DCR; a spool restrictor is used as the first step restrictor. By changing the restrictor resistance of the spool restrictor, the effect of the active control in the DCR, the second step restrictor, can be altered. The proposed DCR is incorporated into a hydrostatic bearing supporting a precision spindle, and the performance of the bearing is analyzed. Numerical and experimental analyses show that the stiffness of the hydrostatic bearing with the proposed DCR can be five times as large as a conventional hydrostatic bearing of the same dimensions. Analysis of the dynamic compliance shows that the effect of the active control can be observed up to 20Hz. These results show that the proposed DCR is useful for improving the performance of the hydrostatic-bearing spindle in precision applications.

Binocular robot vision system with autonomous movement of viewpoint

A binocular robot vision system having an autonomously moving active viewpoint is proposed. By using this active viewpoint, the system constructs a correspondence between the images of a feature points on the right and left retinas easily and calculates the spatial coordinates of the feature points. The system incorporates two intelligent functions for enlarging the measuring region and increasing the accuracy of measurement. The first intelligent function is an autonomous movement of the viewpoint and the second is weighting process for measured points. These functions work when the system can recognize the solid body. As the first steps of the development of the recognition of a solid body, we incorporate these functions into the system to detect straight lines in an image. To detect lines we use Hough transform. The system searches a region surrounded by 4 straight lines. Then the system recognizes the region as a quadrangle. The system constructs a correspondence between the quadrangles in the right and left images. By the use of the result of the constructed correspondence, the system calculates the spatial coordinates of an object. An experiment shows the effect of the line detection using Hough transform, the recognition of the surface of the object and the calculation of the spatial coordinates of the object.

An autonomous robot controlled by stereovision system using two-layer LCD for tracking object

A novel stereo robot vision system using a two-layer crystal display ( LCD ) is proposed. The images of an object captured by right and left CCD cameras are displayed on the two-layer LCD. The light intensity transmitted through the two-layer LCD depends on the degree of matching between the images of two cameras. Therefore, the distance from the cameras to the object can be deduced from the transmitted light intensity without using sophisticated computer algorithm. An example of the application of this stereovision system for the autonomous robot is presented.

Binocular Robot Vision with Active Viewpoint for Sphere Measurement

A binocular robot vision system reconstructs 3D scenes from right and left images by using triangulation. However when using triangulation, the corresponding problems have to be resolved. To resolve the corresponding problems easily, authors have proposed a binocular robot vision system with an autonomously moving active viewpoint. By using this active viewpoint, the system constructs the correspondence between images of feature points of an object on the right and left images and calculates the spatial coordinates of the feature points. However the system cannot achieve correspondence between right and left images for smooth surface without feature points like corners. In this paper, we propose a method to extract feature points on a smooth surface virtually. To extract the feature points on the smooth surface of an object virtually, we use an active viewpoint of our system and vergence motion of the right and left cameras. In this system, the right and left cameras viewpoints are corresponded mechanically by the active viewpoint and vergence motion of both cameras. As the virtual feature point, a contact point between the smooth surface and tangential line from the epipole on the baseline of right and left cameras is extracted from the camera images. Because the right and left cameras viewpoints are fixed by the active viewpoint, the active viewpoint becomes the constraint for the extraction of the virtual feature points. The information of the virtual feature points on the smooth surface of an object is used for the calculation of the spatial coordinates of the object. The effect of the proposed method to extract the feature points virtually is shown experimentally by using a sphere as an object.

An Autonomous Vehicle Controlled by Stereo Robot Vision System using Two-Layer LCD

Abstract This paper propsese a novel stereo robot visio system that uses a two-layer liquid crystal display(LCD) to control an autonomous vehicle. Images of an object captured by right and left CCD cameras mounted on the vehicle are displayed on the two-layer LCD. The intensity of the light transmitted light without using a sophisticated computer algorithm. An example of drafting is shown; according to its distance from the vehicle driving ahead, the autonomous vehicle advances, stops or retreats for keeping proper following distance.