Large Language Models as Zero-Shot Human Models for Human-Robot Interaction

TL;DR

This paper investigates the use of large language models as zero-shot human models in human-robot interaction, demonstrating their potential to improve robot planning and interaction in social scenarios.

Contribution

It introduces a novel application of LLMs as human models in HRI, showing they can perform comparably to purpose-built models and be integrated into robot planning.

Findings

LLMs achieve performance comparable to purpose-built models on social datasets.

Planning with LLM-based human models can improve robot task performance.

Preliminary robot experiments show potential benefits of LLM-based human modeling.

Abstract

Human models play a crucial role in human-robot interaction (HRI), enabling robots to consider the impact of their actions on people and plan their behavior accordingly. However, crafting good human models is challenging; capturing context-dependent human behavior requires significant prior knowledge and/or large amounts of interaction data, both of which are difficult to obtain. In this work, we explore the potential of large-language models (LLMs) -- which have consumed vast amounts of human-generated text data -- to act as zero-shot human models for HRI. Our experiments on three social datasets yield promising results; the LLMs are able to achieve performance comparable to purpose-built models. That said, we also discuss current limitations, such as sensitivity to prompts and spatial/numerical reasoning mishaps. Based on our findings, we demonstrate how LLM-based human models can be integrated into a social robot's planning process and applied in HRI scenarios. Specifically, we present one case study on a simulated trust-based table-clearing task and replicate past results that relied on custom models. Next, we conduct a new robot utensil-passing experiment (n = 65) where preliminary results show that planning with a LLM-based human model can achieve gains over a basic myopic plan. In summary, our results show that LLMs offer a promising (but incomplete) approach to human modeling for HRI.