Visual servoing with independently controlled cameras using a learned invariant representation

Robots that use an active camera system for visual feedback can achieve greater flexibility, including the ability to operate in a dynamically changing environment. Incorporating active vision into a robot control loop involves some inherent difficulties, including calibration, and the need for redefining the goal as the camera configuration changes. We propose a self-organizing neural network that learns a calibration-free spatial representation of 3D point targets in a manner that is invariant to changing camera configurations. This learned representation is used as the basis for developing a novel framework for robot control with active vision. The salient feature of this framework is that it decouples active camera control from robot control. The feasibility of this approach is explored with the help of computer simulations and experiments with an active camera system.