Grasping Objects of Various Shapes
by Calibration-Free Vision-Guided Robots
Abstract
An approach to vision-based control of calibration-free robots is introduced. Similarly to living organisms, it uses an uncalibrated stereo vision system, but no world coordinates and no inverse perspective or kinematic transformations, and it enables an automatic adaptation to changing optical, mechanical and control parameters of the robot.
We implemented the approach on a vision-guided calibration-free articulated arm manipulator with five degrees of freedom. In real-word grasping experiments we showed that the robot control without calibration is, indeed, feasible and that it leads to robots with a remarkable degree of robustness against disturbances of the sensors and unexpected changes of the robot’s parameters.