USPilot: An Embodied Robotic Assistant Ultrasound System with Large Language Model Enhanced Graph Planner

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Mingcong, Fan, Siqi, Cao, Guanglin, Liu, Yun-hui, Liu, Hongbin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910973560881152
author Chen, Mingcong
Fan, Siqi
Cao, Guanglin
Liu, Yun-hui
Liu, Hongbin
author_facet Chen, Mingcong
Fan, Siqi
Cao, Guanglin
Liu, Yun-hui
Liu, Hongbin
contents In the era of Large Language Models (LLMs), embodied artificial intelligence presents transformative opportunities for robotic manipulation tasks. Ultrasound imaging, a widely used and cost-effective medical diagnostic procedure, faces challenges due to the global shortage of professional sonographers. To address this issue, we propose USPilot, an embodied robotic assistant ultrasound system powered by an LLM-based framework to enable autonomous ultrasound acquisition. USPilot is designed to function as a virtual sonographer, capable of responding to patients' ultrasound-related queries and performing ultrasound scans based on user intent. By fine-tuning the LLM, USPilot demonstrates a deep understanding of ultrasound-specific questions and tasks. Furthermore, USPilot incorporates an LLM-enhanced Graph Neural Network (GNN) to manage ultrasound robotic APIs and serve as a task planner. Experimental results show that the LLM-enhanced GNN achieves unprecedented accuracy in task planning on public datasets. Additionally, the system demonstrates significant potential in autonomously understanding and executing ultrasound procedures. These advancements bring us closer to achieving autonomous and potentially unmanned robotic ultrasound systems, addressing critical resource gaps in medical imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle USPilot: An Embodied Robotic Assistant Ultrasound System with Large Language Model Enhanced Graph Planner
Chen, Mingcong
Fan, Siqi
Cao, Guanglin
Liu, Yun-hui
Liu, Hongbin
Robotics
In the era of Large Language Models (LLMs), embodied artificial intelligence presents transformative opportunities for robotic manipulation tasks. Ultrasound imaging, a widely used and cost-effective medical diagnostic procedure, faces challenges due to the global shortage of professional sonographers. To address this issue, we propose USPilot, an embodied robotic assistant ultrasound system powered by an LLM-based framework to enable autonomous ultrasound acquisition. USPilot is designed to function as a virtual sonographer, capable of responding to patients' ultrasound-related queries and performing ultrasound scans based on user intent. By fine-tuning the LLM, USPilot demonstrates a deep understanding of ultrasound-specific questions and tasks. Furthermore, USPilot incorporates an LLM-enhanced Graph Neural Network (GNN) to manage ultrasound robotic APIs and serve as a task planner. Experimental results show that the LLM-enhanced GNN achieves unprecedented accuracy in task planning on public datasets. Additionally, the system demonstrates significant potential in autonomously understanding and executing ultrasound procedures. These advancements bring us closer to achieving autonomous and potentially unmanned robotic ultrasound systems, addressing critical resource gaps in medical imaging.
title USPilot: An Embodied Robotic Assistant Ultrasound System with Large Language Model Enhanced Graph Planner
topic Robotics
url https://arxiv.org/abs/2502.12498