Visual servoing using triangulation with an omnidirectional multi-camera system

Abstract

In this paper a new approach for robot control using position based visual servoing (PBVS) with an omnidirectional multi-camera system is presented. PBVS requires the explicit calculation of the position and orientation of the robot tool. Given only images without depth information, either additional geometric properties of the observed scene or stereo correspondences have to be provided for pose estimation. In this paper we use triangulation of images given by many cameras pointing in various directions. We confirm this approach with some simulational results.

Hand-eye servo and impedance control for manipulator arm to capture target satellite safely

“…Visual servoing schemes are generally classified into position-based visual servo (PBVS) and image-based visual servo (IBVS). 18 In the PBVS approach, 19,20 the controller is designed using the relative three-dimensional (3D) pose between the camera and the target object, which is estimated from the visual features. However, this approach is sensitive to camera calibration and needs a priori 3D model of the target object for the 3D reconstruction.…”

Cloud-Based Networked Visual Servo Control

“…From 'look-and-move' [1] approaches in open loop fashion to 'visual servoing' [2]- [5] in closed loop fashion, the performance of vision-based control systems benefits from the developments of the sensing technology (e.g. networked cameras [6], camera arrays [7], dense skins of cameras [8]), image processing techniques (e.g. applying image moments [9], Laplacian of Gaussian [10], and wavelets [11] for feature extraction), and different control schemes (e.g.…”