Particle filtering for position based 6DOF visual servoing in industrial environments

Visual servoing allows the introduction of robotic manipulation in dynamic and uncontrolled environments. This paper presents a position-based visual servoing algorithm using particle filtering. The objective is the grasping of objects using the 6 degrees of freedom of the robot manipulator (position and orientation) in nonautomated industrial environments using monocular vision. A particle filter has been added to the positionbased visual servoing algorithm to deal with the different noise sources of those industrial environments (metallic nature of the objects, dirt or illumination problems). This addition allows dealing with those uncertainties and being able to recover from errors in the grasping process. Experiments performed in the real industrial scenario of ROBOFOOT project showed accurate grasping and high level of stability in the visual servoing process.