To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions
This addresses the challenge of seamless human-robot collaboration in social settings, though it appears incremental as it builds on existing LLM and robotics techniques.
The paper tackles the problem of enabling robots to provide unobtrusive physical support in human group interactions by introducing Attentive Support, a concept that integrates scene perception, dialogue, situation understanding, and behavior generation with LLMs, resulting in a robot that can decide when and how to help or remain silent without disturbing the group, as demonstrated through evaluation in diverse scenarios.
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.