Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach called Staged Social Behavior Learning (SSBL) that enables robots to learn socially appropriate approaching behaviors towards human groups in simulation and real-world interactions.

Contribution

The paper presents a novel staged learning scheme that transfers social approaching behaviors from simulation to real robots, improving social appropriateness in HRI.

Findings

Model generates more socially appropriate behavior than previous models.

Approach validated through perceptual and user studies with positive results.

Effective transfer of learned behaviors from simulation to real-world robots.

Abstract

Deep reinforcement learning has recently been widely applied in robotics to study tasks such as locomotion and grasping, but its application to social human-robot interaction (HRI) remains a challenge. In this paper, we present a deep learning scheme that acquires a prior model of robot approaching behavior in simulation and applies it to real-world interaction with a physical robot approaching groups of humans. The scheme, which we refer to as Staged Social Behavior Learning (SSBL), considers different stages of learning in social scenarios. We learn robot approaching behaviors towards small groups in simulation and evaluate the performance of the model using objective and subjective measures in a perceptual study and a HRI user study with human participants. Results show that our model generates more socially appropriate behavior compared to a state-of-the-art model.