SEAN: Social Environment for Autonomous Navigation

TL;DR

SEAN is an open-source, high-fidelity simulation platform designed to facilitate reproducible evaluation of social navigation algorithms across diverse robotic platforms and environments.

Contribution

The paper introduces SEAN, a novel extensible simulation platform with evaluation toolkit for social navigation, promoting standardized and reproducible algorithm assessment.

Findings

SEAN enables evaluation of navigation algorithms in dynamic pedestrian environments.

Demonstrated with two robot types and environments, showcasing versatility.

Supports reproducible research in social robot navigation.

Abstract

Social navigation research is performed on a variety of robotic platforms, scenarios, and environments. Making comparisons between navigation algorithms is challenging because of the effort involved in building these systems and the diversity of platforms used by the community; nonetheless, evaluation is critical to understanding progress in the field. In a step towards reproducible evaluation of social navigation algorithms, we propose the Social Environment for Autonomous Navigation (SEAN). SEAN is a high visual fidelity, open source, and extensible social navigation simulation platform which includes a toolkit for evaluation of navigation algorithms. We demonstrate SEAN and its evaluation toolkit in two environments with dynamic pedestrians and using two different robots.