Analyzing the Relevance of Features for a Social Navigation Task

Robot navigation in human environments is an active research area that poses serious challenges in both robot perception and actuation. Among them, social navigation and human-awareness have gained lot of attention in the last years due to its important role in human safety and robot acceptance. Several approaches have been proposed; learning by demonstrations stands as one of the most used approaches for estimating the insights of human social interactions. However, typically the features used to model the person-robot interaction are assumed to be given. It is very usual to consider general features like robot velocity, acceleration or distance to the persons, but there are not studies on the criteria used for such features selection. In this paper, we employ a supervised learning approach to analyze the most important features that might take part into the human-robot interaction during a robot social navigation task. To this end, different subsets of features are employed with an AdaBoost classifier and its classification accuracy is compared with that of humans in a social navigation experimental setup. The analysis shows how it is very important not only to consider the robot-person relative poses and velocities, but also to recognize the particular social situation.