SocNavBench: A Grounded Simulation Testing Framework for Evaluating Social Navigation

TL;DR

SocNavBench is a simulation framework with realistic visuals and social scenarios, enabling consistent evaluation of social navigation algorithms through a suite of metrics, fostering comparison and development in the field.

Contribution

It introduces SocNavBench, a grounded simulation testing framework with curated scenarios and metrics, to standardize evaluation of social navigation methods.

Findings

Demonstrated testing of three existing methods and a baseline.

Showed how metrics reveal performance trade-offs.

Open-source code facilitates community contributions.

Abstract

The human-robot interaction (HRI) community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures to evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult to compare the performance of such methods across the literature. To bridge this gap, we introduce SocNavBench, a simulation framework for evaluating social navigation algorithms. SocNavBench comprises a simulator with photo-realistic capabilities and curated social navigation scenarios grounded in real-world pedestrian data. We also provide an implementation of a suite of metrics to quantify the performance of navigation algorithms on these scenarios. Altogether, SocNavBench provides a test framework for evaluating disparate social navigation methods in a consistent and interpretable manner. To illustrate its use, we demonstrate testing three existing social navigation methods and a baseline method on SocNavBench, showing how the suite of metrics helps infer their performance trade-offs. Our code is open-source, allowing the addition of new scenarios and metrics by the community to help evolve SocNavBench to reflect advancements in our understanding of social navigation.