Abstract: Vision is one of the most important sense in humans. Numerous attempts to mimic that powerful sense have been the main topic of extensive robotic research for decades. Demonstrated applications of vision control in which information acquired from camera(s) is used for guiding a robot system, span the broad range of human activity and include well-known theoretical, as well as practical knowledge of visual servoing themes. Visual servoing problem is, in fact, the problem of systems of nonlinear equations solving, which is a mature and well founded mathematical area with rich foundations of papers, studying the various type of problems with appropriate approaches. Uncalibrated, model free, robot visual servoing has been widely applicable in robot vision due to minimal requirements related to calibration and robot kinematic’s parameters. The appropriate solutions are mostly derived from quasy-Newton approach for the nonlinear problem solving and represent various iterative approaches for acquiring an optimal solution.
However, if the robot has been controlled in the unstructured environments, the mentioned problem has been proven hard as the real system has been influenced with the noise.. Up to now, there are numerous examples which successfully use described approach for robot visual servoing. The numerical quasy-Newton methods serves as a theoretical background for problem solving, which has been proven hard as the real system has been influenced with the noise. Consequently, additional attention has to be paid which assured stability and the robustness of the proposed method. Various methods offer specific improvements which are related mostly to the specific task requirements. This lecture has a goal to present and compare the efficacy of the various iterative optimization procedures which, due to their successfulness, established itself as a paradigm for appropriate problem solving.

Brief Biography of the Speaker:
Mirjana Bonkovic received the B.S., M.S., and PhD. Degrees in electrical engineering from the University of Split, Split, Croatia, in 1990, 1994, and 2000, respectively.
Since 1991, she has worked at the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, where she currently serves as associate professor. She was a visiting student at Robotics Research Group, University of Oxford, U.K., in 1995, and Visiting Research Fellow at the Institute of Robotics, University of Maribor, Slovenia, in 2004. Her research interests are image processing, pattern recognition, robot vision and bio-mimetic systems. She is author of more than 30 scientific papers published at international conferences and journals.