Homography-Based Visual Servoing of Eye-in-Hand Robots With Exact Depth Estimation

Visual servoing can effectively control robots using visual feedback to improve their intelligence and reliability. For a feature point detected by a monocular camera, the time-varying depth appearing nonlinearly in the Jacobian matrix is difficult to be measured without the prior geometry knowledge of the observed object. Therefore, the depth of the feature point is one of the major uncertain parameters in visual servoing. Considering unknown Cartesian feature positions, this article presents a robot dynamics-based homography-based visual servoing (HBVS) controller for the 3-D pose regulation of eye-in-hand robot arms with monocular cameras. The uncertain depth is represented into a linear form of its Cartesian feature position, and a composite learning law is applied to estimate position parameters accurately, resulting in exact depth estimation. Compared to existing adaptive HBVS methods, the distinctive feature of the proposed method is that it is a dynamics-based design and guarantees exact depth estimation under a much weaker condition termed interval excitation compared to persistent excitation. Simulations and experiments on a collaborative robot with seven degrees of freedom named Franka Emika Panda have verified the effectiveness of the proposed method.