Abstract
As mobile robots are increasingly introduced into our daily lives, it grows ever more imperative that these robots navigate with and among people in a safe and socially acceptable manner, particularly in shared spaces. While research on enabling socially-aware robot navigation has expanded over the years, there are no agreed-upon evaluation protocols or benchmarks to allow for the systematic development and evaluation of socially-aware navigation. As an effort to aid more productive development and progress comparisons, in this paper we review the evaluation methods, scenarios, datasets, and metrics commonly used in previous socially-aware navigation research, discuss the limitations of existing evaluation protocols, and highlight research opportunities for advancing socially-aware robot navigation.