Model based visual servoing tasks with an autonomous humanoid robot

Many model based techniques have been proposed in the literature for applying domestic service tasks on humanoid robots, such as teleoperation, learning from demonstration and imitation. However sensor based robot control overcomes many of the difficulties of uncertain models and unknown environments which limit the domain of application of the previous methods. Furthermore, for service and manipulation tasks, it is more suitable to study the interaction between the robot and its environment at the contact point using the sensor based control, rather than specifying the joint positions and velocities required to achieve them. In this work we present an integration of real-time visual servoing techniques on a humanoid robot in closed loop, to perform self-localization and different manipulation tasks. Indeed, real-time model based tracking techniques are used to apply 3D visual servoing tasks on the Nao humanoid robot. The elementary tasks which are used by the robot to perform a concrete service scenario are detailed with their corresponding control laws. Finally, we present the experimental results of the following tasks: self-localization of the robot while walking, head servoing for the visibility task, detection, tracking and manipulation of environment's objects.