To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions

TL;DR

This paper introduces Attentive Support, a novel robot interaction system that uses LLMs to unobtrusively support human groups by understanding situations and deciding when to intervene or remain silent.

Contribution

It presents a new approach combining scene perception, dialogue, and LLM reasoning to enable robots to support human groups effectively without disturbance.

Findings

Robot effectively supports humans when needed

Supports diverse scenarios with unobtrusive behavior

Decides when to support or stay silent

Abstract

How can a robot provide unobtrusive physical support within a group of humans? We present Attentive Support, a novel interaction concept for robots to support a group of humans. It combines scene perception, dialogue acquisition, situation understanding, and behavior generation with the common-sense reasoning capabilities of Large Language Models (LLMs). In addition to following user instructions, Attentive Support is capable of deciding when and how to support the humans, and when to remain silent to not disturb the group. With a diverse set of scenarios, we show and evaluate the robot's attentive behavior, which supports and helps the humans when required, while not disturbing if no help is needed.