An Intelligent Human Avatar to Debug and Challenge Human-aware Robot Navigation Systems

Experimenting, testing, and debugging robot social navigation systems is a challenging task. While simulation is generally well suited for a first level of debugging and evaluation of robotics controllers and planners, the social navigation field lacks satisfactory simulators of humans which act, react and interact rationally and naturally. To facilitate the development of human-aware navigation systems, we propose a system to simulate an autonomous human agent that is both reactive and rational, specifically designed to act and interact with a robot for navigation problems and potential conflicts. Besides, it also provides some metrics to partially evaluate such interactions and data logs for further analysis. We show the limitations of over-used reactive-only approaches. Then, thanks to two different human-aware navigation planners, we show how our system can help answer the lack of intelligent human avatars for tuning and debugging social navigation systems before their final evaluation with real humans.