Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task

TL;DR

This paper explores using large language models to predict human intentions in a collaborative object categorization task with a robot, integrating multimodal cues for improved interaction.

Contribution

It introduces a novel multimodal hierarchical approach leveraging LLMs to infer human intentions from verbal and non-verbal cues in human-robot collaboration.

Findings

LLMs can effectively reason about multimodal user cues

The approach improves intention prediction accuracy

Leveraging context and real-world knowledge enhances interaction

Abstract

Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior proactively. Therefore, intention prediction is pivotal in creating a natural interaction with social robots in human-designed environments. In this paper, we examine using Large Language Models (LLMs) to infer human intention in a collaborative object categorization task with a physical robot. We propose a novel multimodal approach that integrates user non-verbal cues, like hand gestures, body poses, and facial expressions, with environment states and user verbal cues to predict user intentions in a hierarchical architecture. Our evaluation of five LLMs shows the potential for reasoning about verbal and non-verbal user cues, leveraging their context-understanding and real-world knowledge to support intention prediction while collaborating on a task with a social robot. Video: https://youtu.be/tBJHfAuzohI