The present workshop focuses on the topic of intention recognition in HRI. To be able to recognise intentions of other agents is a fundamental prerequisite to engage in, for instance, instrumental helping or mutual collaboration. It is a necessary aspect of natural interaction. In HRI, the problem is therefore bi-directional: not only does a robot need the ability to infer intentions of humans; humans also need to infer the intentions of the robot. From the human perspective, this inference draws both on the ability to attribute cognitive states to lifeless shapes, and the ability to understand actions of other agents through, for instance, embodied processes or internal simulations (i.e the human ability to form a theory of mind of other agents). How precisely, and to what degree these mechanisms are at work when interacting with social artificial agents remains unknown. From the robotic perspective, this lack of understanding of mechanisms underlying human intention recognition, or the capacity for theory of mind in general, is also challenging: the solution can, for instance, not simply be to make autonomous systems work "just like" humans by copying the biological solution and implementing some technological equivalent. It is therefore important to be clear about the theoretical framework(s) and inherent assumptions underlying technological implementations related to mutual intention. This remains very much an active research area in which further development is necessary. The core purpose of this workshop is thus to contribute to and advance the state of the art in this area.