用大模型让轮椅助餐机器人听懂人话，老人也能自然指挥。
Towards an LLM-Based Speech Interface for Robot-Assisted Feeding
- 基于大模型设计可迭代的语音交互框架，贴近用户需求。
- 11位老年人参与测试，系统能准确理解自然语言指令。
- 适合残障人士及老年群体，提升生活独立性。
物理辅助机器人有望显著提升因运动障碍或其他残疾而无法完成日常活动（ADL）的人群的生活质量与独立性。语音接口，特别是利用大语言模型（LLM）的接口，能够使人以高效且自然的方式向机器人传达高层次命令和细微偏好。本文展示了一种基于大语言模型的语音接口，用于商用辅助喂食机器人。该系统建立在《VoicePilot：利用大语言模型作为物理辅助机器人语音接口》一文提出的迭代式设计框架基础上，融入了以人为本的设计元素，使大语言模型更适合作为机器人交互界面。系统通过一项针对11名居住在独立生活设施中的老年人的用户研究进行了评估。视频演示可见于项目网站：https://sites.google.com/andrew.cmu.edu/voicepilot/。
原文摘要 · Abstract (English)
Physically assistive robots present an opportunity to significantly increase the well-being and independence of individuals with motor impairments or other forms of disability who are unable to complete activities of daily living (ADLs). Speech interfaces, especially ones that utilize Large Language Models (LLMs), can enable individuals to effectively and naturally communicate high-level commands and nuanced preferences to robots. In this work, we demonstrate an LLM-based speech interface for a commercially available assistive feeding robot. Our system is based on an iteratively designed framework, from the paper "VoicePilot: Harnessing LLMs as Speech Interfaces for Physically Assistive Robots," that incorporates human-centric elements for integrating LLMs as interfaces for robots. It has been evaluated through a user study with 11 older adults at an independent living facility. Videos are located on our project website: https://sites.google.com/andrew.cmu.edu/voicepilot/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。