arXiv 2603.088172026-03-09cs.RO

HMR-1: 基于视觉-语言模型的分层按摩机器人用于具身医疗

HMR-1: Hierarchical Massage Robot with Vision-Language-Model for Embodied Healthcare

The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；Spatiotemporal AI, China（时空人工智能，中国）；Hangzhou International Innovation Institute, Beihang University, China（杭州国际创新研究院，北航，中国）；Georgia Institute of Technology, China（佐治亚理工学院，中国）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education（计算功率网络与信息安全重点实验室，教育部；山东省计算机科学中心，齐鲁工业大学（山东省科学院），中国）；Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), China

Rongtao Xu, Mingming Yu, Xiaofeng Han, Yu Zhang, Kaiyi Hu, Zhe Feng, Zenghuang Fu, Changwei Wang, Weiliang Meng, Xiaopeng Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

HMR-1提出基于视觉-语言模型的分层按摩机器人框架，通过构建多模态数据集和微调Qwen-VL模型，实现了具身医疗任务的评估与应用。

摘要：

具身智能的快速发展为医疗领域，特别是物理治疗和康复提供了变革性机会。然而，在开发稳健的具身医疗解决方案方面仍存在关键挑战，例如缺乏标准化评估基准和开放源码多模态穴位按摩数据集的稀缺性。为解决这些差距，我们构建了MedMassage-12K数据集，包含12,190张图像和174,177个问答对，涵盖多样的光照条件和背景。此外，我们提出了一种分层具身按摩框架，包括一个高级穴位定位模块和一个低级控制模块。高级穴位定位模块利用多模态大语言模型来理解人类语言并识别穴位位置，而低级控制模块则提供计划的轨迹。基于此，我们评估了现有MLLMs并建立了具身按摩任务的基准。此外，我们微调了Qwen-VL模型，证明了该框架的有效性。物理实验进一步证实了该框架的实用性。我们的数据集和代码已公开在https://github.com/Xiaofeng-Han-Res/HMR-1。

英文摘要：

The rapid advancement of Embodied Intelligence has opened transformative opportunities in healthcare, particularly in physical therapy and rehabilitation. However, critical challenges remain in developing robust embodied healthcare solutions, such as the lack of standardized evaluation benchmarks and the scarcity of open-source multimodal acupoint massage datasets. To address these gaps, we construct MedMassage-12K - a multimodal dataset containing 12,190 images with 174,177 QA pairs, covering diverse lighting conditions and backgrounds. Furthermore, we propose a hierarchical embodied massage framework, which includes a high-level acupoint grounding module and a low-level control module. The high-level acupoint grounding module uses multimodal large language models to understand human language and identify acupoint locations, while the low-level control module provides the planned trajectory. Based on this, we evaluate existing MLLMs and establish a benchmark for embodied massage tasks. Additionally, we fine-tune the Qwen-VL model, demonstrating the framework's effectiveness. Physical experiments further confirm the practical applicability of the framework.Our dataset and code are publicly available at https://github.com/Xiaofeng-Han-Res/HMR-1.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。