Learning a Group-Aware Policy for Robot Navigation

TL;DR

This paper introduces a deep reinforcement learning approach for robot navigation that accounts for human groups, leading to safer, more socially acceptable robot movements in human environments.

Contribution

It presents a novel group-aware navigation policy that considers dynamic human group formations, improving social compliance and navigation efficiency.

Findings

Group-aware policies reduce collisions and social norm violations.

Robots with group-aware policies cause less discomfort to pedestrians.

The approach outperforms baseline methods in simulation experiments.

Abstract

Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments. While prior research has mostly focused on modeling pedestrians as independent, intentional individuals, people move in groups; consequently, it is imperative for mobile robots to respect human groups when navigating around people. This paper explores learning group-aware navigation policies based on dynamic group formation using deep reinforcement learning. Through simulation experiments, we show that group-aware policies, compared to baseline policies that neglect human groups, achieve greater robot navigation performance (e.g., fewer collisions), minimize violation of social norms and discomfort, and reduce the robot's movement impact on pedestrians. Our results contribute to the development of social navigation and the integration of mobile robots into human environments.