Rethinking Social Robot Navigation: Leveraging the Best of Two Worlds

TL;DR

This paper proposes a hybrid social robot navigation system that combines geometric and learning-based methods, leveraging their respective strengths to improve social compliance in navigation tasks, validated through experiments on datasets and physical robots.

Contribution

It introduces a hybrid navigation framework that switches between geometric and learning-based planning, demonstrating improved social compliance over individual methods.

Findings

Hybrid planner outperforms individual approaches in social compliance.

Geometric systems can produce human-like trajectories in many social situations.

The hybrid approach is validated on real-world datasets and physical robots.

Abstract

Empowering robots to navigate in a socially compliant manner is essential for the acceptance of robots moving in human-inhabited environments. Previously, roboticists have developed geometric navigation systems with decades of empirical validation to achieve safety and efficiency. However, the many complex factors of social compliance make geometric navigation systems hard to adapt to social situations, where no amount of tuning enables them to be both safe (people are too unpredictable) and efficient (the frozen robot problem). With recent advances in deep learning approaches, the common reaction has been to entirely discard these classical navigation systems and start from scratch, building a completely new learning-based social navigation planner. In this work, we find that this reaction is unnecessarily extreme: using a large-scale real-world social navigation dataset, SCAND, we find that geometric systems can produce trajectory plans that align with the human demonstrations in a large number of social situations. We, therefore, ask if we can rethink the social robot navigation problem by leveraging the advantages of both geometric and learning-based methods. We validate this hybrid paradigm through a proof-of-concept experiment, in which we develop a hybrid planner that switches between geometric and learning-based planning. Our experiments on both SCAND and two physical robots show that the hybrid planner can achieve better social compliance compared to using either the geometric or learning-based approach alone.