Towards Benchmarking Human-Aware Social Robot Navigation: A New Perspective and Metrics

Phani-Teja Singamaneni, Anthony Favier, Rachid Alami

Abstract: Human-aware robot navigation planning enables robots to traverse human-occupied spaces socially. However, evaluating and benchmarking the ‘human awareness’ of such navigation schemes is challenging. With the growing necessity and research interest in the field, there is a need to define metrics to quantify and benchmark such qualities. In this regard, this paper proposes a set of metrics by looking at the problem from a new perspective. These proposals are made by inspecting the robot’s navigation from the viewpoint of a human experiencing it and then defining proxies for the perceived human feelings. Analyses of some commonly occurring human-robot navigation scenarios using these metrics show their capability in benchmarking and differentiating human-aware robot navigation from standard robot navigation.