Vision in the Loop for Force and Position Control of the Robot Manipulators

Over the last decades, both force sensors and cameras have developed as useful sensors for different applications in robotics. This thesis considers a number of dynamic visual tracking and control problems, as well as the integration of these techniques with contact force control. Different topics ranging from basic theory to system implementation and applications are treated. It addresses the use of monocular eye-in-hand machine vision to control the position of a robot manipulator for dynamically challenging tasks. Such tasks are defined as those where the robot motion required approaches or exceeds the performance limits stated by the manufacturer. Computer vision systems have been used for robot control for over four decades now, but have rarely been used for high-performance visual closed-loop control. This has largely been due to technological limitations in image processing, but since the mid 2010s advances have made it feasible to apply computer vision techniques at a sufficiently high rate to guide a robot or close a feedback control loop. Visual servoing is the use of computer vision for closed-loop control of a robot manipulator, and has the potential to solve a number of problems that currently limit the potential of robots in industry and advanced applications. In this thesis we have developed an algorithm that can extract high accurate position of object from vision data. This can be used as proximity sensor, in harsh environments. In order to achieve high-performance it is necessary to have accurate models of the system to be controlled (the robot) and the sensor (the camera and vision system). Despite the long history of research in these areas individually, and combined in visual servoing, it is apparent that many issues have not been addressed in sufficient depth, and that much of the relevant information is spread through a very diverse literature. A new filter based on the wavelet multi resolution structures has been developed that can fuse position from camera and acceleration data from MEMS and produce velocity estimations which have lowest delay and drift with highest resolution at output. Also in the empirical and theoretical way, we have studied over robotic actuators specially brushless DC motors. Outputs of these studies are one designed and implemented advanced brushless driver, which can control the brushless motors of medium power around $300[W]$ in position and velocity mode.