In recent years there has been a large focus on how robots can operate in human populated environments. In this paper, we focus on interactions between humans and small indoor robots and introduce a new human-robot interaction (HRI) dataset. The analysis of the recorded experiments shows that anticipatory and non-reactive robot controllers impose similar constraints to humans' safety and efficiency. Additionally, we found that current state-of-the-art models for human trajectory prediction can adequately extend to indoor HRI settings. Finally, we show that humans respond differently in shared and homogeneous environments when collisions are imminent, since interacting with small differential drives can only cause a finite level of social discomfort as compared to human-human interactions. The dataset used in this analysis is available at: https://github.com/AlexanderDavid/ZuckerDataset.

翻译：近年来，机器人如何在人类活动环境中运行成为研究焦点。本文聚焦于人类与小型室内机器人之间的交互，并引入了一个新的人机交互（HRI）数据集。对记录实验的分析表明，预期性和非反应性机器人控制器对人类安全性与效率施加了相似的约束。此外，我们发现当前最先进的人类轨迹预测模型能够充分适用于室内人机交互场景。最终，我们证明在共享与同质化环境中，当碰撞即将发生时人类的反应存在差异——相较于人际交互，与小型差动驱动机器人的交互仅会引发有限程度的社会不适感。本分析所用的数据集可通过以下链接获取：https://github.com/AlexanderDavid/ZuckerDataset。