Preference Modeling of Spatial Description in Human-Robot Interaction

Spatial description plays an important role in the design of human-robot interaction systems for intelligent robots. In this paper, we model the preference of the types of spatial description by collecting spatial constructions in two groups of tabletop task experiments, where the participants use spatial constructions to instruct the partner (human/robot) to pick up an indicated object. The preference modeling process is implemented by analyzing the probabilistic distribution of different types of spatial description (including different reference frames) of these participants in five typical scenarios regarding the partners of human and robot, respectively. The results provide a basis for the design of collaborative robots when interacting with people and will help improve the efficiency of human-centered human-robot interaction.