Effective communication is vital in healthcare, especially across language barriers, where non-verbal cues and gestures are critical. This paper presents a privacy-preserving vision-language framework for medical interpreter robots that detects specific speech acts (consent and instruction) and generates corresponding robotic gestures. Built on locally deployed open-source models, the system utilizes a Large Language Model (LLM) with few-shot prompting for intent detection. We also introduce a novel dataset of clinical conversations annotated for speech acts and paired with gesture clips. Our identification module achieved 0.90 accuracy, 0.93 weighted precision, and a 0.91 weighted F1-Score. Our approach significantly improves computational efficiency and, in user studies, outperforms the speech-gesture generation baseline in human-likeness while maintaining comparable appropriateness.
@article{arxiv.2603.05751,
title = {Vision-Language System using Open-Source LLMs for Gestures in Medical Interpreter Robots},
author = {Thanh-Tung Ngo and Emma Murphy and Robert J. Ross},
journal= {arXiv preprint arXiv:2603.05751},
year = {2026}
}