AUVs have experimentally done the first steps to solve basic intervention tasks. First results have been promising in the task of retrieving an object from the seabed. In this paper we extend the complexity of the task with the help of a Learning by Demonstration (LbD) approach. An extension of a LbD algorithm to learn the pose and orientation of the trajectory is presented to achieve a valve turning task. A batch of demonstrations done in ROV mode is used by the LbD to learn the trajectory, taking advantage of the experience of the pilots. Moreover, the paper present a controller able to coordinate the movement of the manipulator using the position or the orientation of the end-effector and also moving the AUV when is required. Both systems have been tested together in a simulated environment to solve the task of interacting with a valve located on a ROV panel. The experiments has been done in an environment without perturbations and in an environment with different perturbations. The method has been able to overcome the perturbations and complete the task successfully. Furthermore, the proposed controller has simplified the use of the manipulator during the intervention task. The robot is equipped with a 4 DOFs manipulator having a griper as end effector to operate the T bar handles found in the panel. Panel and valve handle position and orientation are detected by a computer vision program based on template matching. © 2013 IEEE.