This work aims at designing a visual predictive control (VPC) scheme for a mobile manipulator. It consists in combining image-based visual servoing with model predictive control to benefit from the advantages of both control structures. Two challenges are addressed in this paper: the choice of the visual features and the closed-loop stability. The first ones rely on image moments to improve the end effector positioning precision. The second one is tackled through a terminal constraint coupled with suitable input constraints to reduce the computational burden. Simulation results using ROS and Gazebo validate the proposed approach.

This work aims at designing a visual predictive control (VPC) scheme for a mobile manipulator equipped with two cameras. The task consists in accurately positioning the endeffector camera while starting a few meters away from the desired pose with a tucked arm. Three challenges are addressed in this paper: the initial unavailability of the visual features, the arm singularities together with the closed-loop stability, and the final positioning accuracy. The first one is dealt with by choosing image features extracted from both cameras and by suitably switching between them, the second one is tackled through a suitable manipulability measure introduced in the cost function, and the two last ones are fulfilled via the definition of an enhanced terminal constraint. The proposed approach has been validated experimentally on TIAGo robot. The obtained results show its relevance and its efficiency.