One application of robotics is to assist humans in the achievement of tasks they face in both the workplace and domestic environments. In some situations, a task may require the robot and the human to act together in a collaborative way in order to reach a common goal. To achieve a collaborative plan, each agent (human, robot) needs to be aware of the tasks she/he must carry out and how to perform them. This paper addresses the issue of enhancing a robotic system with a dynamic model of its collaborator's knowledge concerning tasks of a shared plan. Using this model, the robot is able to adapt its collaborative plan generation, its abilities to give explanations and to monitor the overall plan execution. We present the algorithm we have elaborated to take advantage of the tree representation of our Hierarchical Task Network (HTN) planner to enhance the robot with appropriate explanation and execution monitoring abilities. To evaluate how our adaptive system is perceived by users and how much it improves the quality of the Human-Robot interaction, the outcome of a comparative study is presented.