Navigation Style Classification Using Persistent Homology

Recently, many researchers in the mobile robot field study how to realize socially-aware navigation in human-robot coexisting spaces. However, we have fundamental questions: how can be the socially-aware behavior defined and classified? Our work aims to provide the answers and is divided into two major studies; defining the socially-aware behavior in terms of the traffic psychology and extracting specific patterns to understand the behavior. For the first study, we designed simulation experiments based on the traffic psychology. In the experiments, participants operated an ego-agent to a destination with three different instructions; cooperative, urgent, and non-urgent. We also analyzed differences of the navigation styles and found that the statistical trend of the ego-motion is different in each style. However, it is difficult to find specific patterns in relation between the ego-motion and surrounding situations. This paper focuses on the second study and presents a classification method of the navigation styles using persistent homology (PH). We consider that implicit patterns could be extracted from surrounding situations by PH because it could enable to find specific patterns from data even when they seem to be distributed randomly. Results show the possibility that the PH-based method could acquire effective information for the classification.