Abstract
In this paper series, we argue for the role embodiment plays in the evaluation of systems developed for Human Computer Interaction. We use a simulation platform, VoxWorld, for building Embodied Human Computer Interactions (EHCI). VoxWorld enables multimodal dialogue systems that communicate through language, gesture, action, facial expressions, and gaze tracking, in the context of task-oriented interactions. A multimodal simulation is an embodied 3D virtual realization of both the situational environment and the co-situated agents, as well as the most salient content denoted by communicative acts in a discourse. It is built on the modeling language VoxML, which encodes objects with rich semantic typing and action affordances, and actions themselves as multimodal programs, enabling contextually salient inferences and decisions in the environment. Through simulation experiments in VoxWorld, we can begin to identify and then evaluate the diverse parameters involved in multimodal communication between agents. In this second part of this paper series, we discuss the consequences of embodiment and common ground, and how they help evaluate parameters of the interaction between humans and agents, and compare and contrast evaluation schemes enabled by different levels of embodied interaction.