Visual servoing refers to a technology using visual information to conduct robotics realtime feedback control, it has always been a hot and difficult problem.
Though researchers have proposed several methods such as 2 1/2 visual servoing (Malis, 1999), 5D visual servoing (Malis, 2014), switched visual servoing (Allibert, 2014) and two-stage visual servoing (Ye, 2015) to improve the performance of motion, there are still some limitations and the problem of multi-constraint handling is hard to solve.
In order to improve the motion characteristics of visual servoing, a set of invariant features with nice decoupling and linear properties is chosen.
Original developments will be required for 3D sensing of semi-regular surfaces with physical texture (overgrown plant surfaces), coping with outdoor lighting variations, self-localising and navigating over real terrain and around obstacles, visual servoing
to align the vehicle with potentially moving target plants, visual servoing
to align leaf and branch cutters to a compliant surface, and innovative engineering to deliver all this on a small battery-powered consumer-grade vehicle.
Since then, for the full-body manipulation, we incorporated depth cameras at the robot wrists and implemented a visual servoing
technique for manipulation tasks that require precision such as valve turning, operating a drill and door opening.
In proposed system, robot ability is not limited with tracking or manipulation ability as it is separated in active vision and visual servoing applications but a fusion of the capabilities from two research field.
This problem, by its nature, is a visual servoing problem where pose error cannot be directly related to sensory and actuators signals but related to integral of them.
Following an introduction to the history of robotics and the Lyapunov-based control philosophy, chapters cover the standard control design tools available for robotic systems within the context of the Lyapunov-based framework; problems in visual servoing
control, including robot end-effector tracking a prerecorded time-varying reference trajectory under visual feedback from a monocular camera, estimating the shape of a continuum robot, tracking and regulation problems of wheeled mobile robots, and the classic Structure from Motion problem.
Key words: visual servoing, CCD camera, MATLAB Simulink, real time driving
The functional model of a robot system using a visual servoing control is presented in this paper.
Development of highly intuitive interfaces for safe human-robot cooperation during assembly by using sensors, visual servoing
, speech recognition, advanced control algorithms