Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation
Provides a benchmark dataset for social robot navigation in constrained spaces, addressing the need for diverse, multimodal data to improve human-robot interaction.
The paper introduces Bi3, a multimodal dataset for social robot navigation featuring close encounters between two humans and a robot, with diverse participants, platforms, and algorithms. Analysis shows it offers unique diversity and modeling complexity for training motion prediction and control policies.
We contribute Bi3, a dataset of social robot navigation among groups of people in a constrained lab space. Compared to prior data collection efforts for social robot navigation, our dataset is unique in that it features: an original experiment design giving rise to close navigation encounters between two humans and a robot; five different navigation algorithms; two different robot platforms; a diverse participant pool of 74 people recruited from two sites in the USA and France; multimodal data streams including 10.5 hours of human and robot ground-truth motion tracks, RGB video, and user impressions over robot performance. Our analysis of the collected dataset through metrics like interaction density and human velocity suggests that Bi3 represents a benchmark of unique diversity and modeling complexity. Bi3 contributes towards understanding how humans and robots can productively mesh their activities in constrained environments, and can be a resource for training models of human motion prediction and robot control policies for navigation in densely crowded spaces.