论文信息 - Closed Loop Robot Control by Real Time Visual Sensor

Closed Loop Robot Control by Real Time Visual Sensor

Abstract This paper deals with a real time K2D visual sensor used to control in a closed loop, a robot which assembles a piece held by its gripper with another one moving in a plane. In a first stage, the visual sensor is modelled and a fast vision algorithm is designed as the means to get the position and the dimensions of a circular pattern in less than 40 ms. In a second stage, the integration of this sensor in a robot unit is investigated and a model is proposed for the asynchronous communication between these two subsystems. In a last step, a feedback structure is studied in order to close the loop in a satisfactory way, and an assembling manipulation is described and analysed.

Gabriel Abba | D. Mehdi | F. Leonard | E. Ostertag

[1] G. Hirzinger,et al. Sensory Feedback in Robotics - State-of-the-Art in Research and Industry , 1987 .

[2] Mongi A. Abidi,et al. Pose estimation for camera calibration and landmark tracking , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[3] Kang G. Shin,et al. A hierarchical system structure for coordinated control of industrial manipulators , 1984, ICRA.

[4] George A. Bekey,et al. Identification of robot dynamics , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[5] Roger Y. Tsai,et al. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..