English

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

Robotics 2025-04-09 v3 Artificial Intelligence Human-Computer 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

Keywords

Cite

@article{arxiv.2404.08424,
  title  = {Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task},
  author = {Hassan Ali and Philipp Allgeuer and Stefan Wermter},
  journal= {arXiv preprint arXiv:2404.08424},
  year   = {2025}
}

Comments

Published in the Proceedings of the 16th International Conference on Social Robotics (ICSR) 2024,15 pages,5 figures,2 tables; work was co-funded by Horizon Europe project TERAIS under Grant agreement number 101079338

R2 v1 2026-06-28T15:52:26.433Z