Visually Guided Control of Robotic Manipulators: Hand-Eye Coordination
Dr. John Gan
Most industrial robotic manipulators move by following fixed trajectories. However, in many applications the environments and tasks of robotic manipulators change dynamically, which bring about various challenges such as dynamic target positioning, trajectory planning, inverse kinematics control, and etc.. Without fixed trajectories, the first problem in robotic manipulator control is where to move, and the second problem is how to move. Visual guidance is the most natural method for solving the first problem. However, 3D computer vision is very difficult, especially when there are constraints on camera positions. In the second problem, the main difficulty lies in the inverse kinematics and dynamics control. We are investigating effective computer vision methods for target positioning, analytical and computational models for inverse kinematics and dynamics, and possible methods to solve where to move and how to move problems together in an integrated manner.