Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation

TL;DR

Bi3 is a diverse, multimodal dataset capturing social robot navigation interactions among humans in constrained environments, designed to advance modeling and control in crowded spaces.

Contribution

It introduces a novel dataset with diverse participants, multiple algorithms, and multimodal data streams for social robot navigation research.

Findings

Dataset includes 10.5 hours of motion data, RGB videos, and user impressions.

Analysis shows the dataset's diversity and complexity as a benchmark.

Bi3 supports training models for human motion prediction and robot control.

Abstract

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.