相关实验视频

Updated: Jun 11, 2025

Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy

Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy

Published on: August 8, 2011

ExTraCT - 基于语言的人机交互的可解释轨迹纠正,使用文本特征描述

J-Anne Yow^1,2, Neha Priyadarshini Garg¹, Manoj Ramanathan¹

¹Rehabilitation Research Institute of Singapore (RRIS), Joint Research Institute by Nanyang Technological University (NTU), Agency for Science, Technology and Research (A∗STAR) and National Healthcare Group (NHG), Singapore, Singapore.

Frontiers in robotics and AI

|October 8, 2024

概括

一个新的框架ExTraCT通过使用自然语言修改机器人路径来增强人机交互. 这种方法更准确,用户更喜欢,改善了机器人任务与人类偏好的调整.

科学领域:

机器人技术机器人技术机器人技术
人与机器人的交互
人工智能的人工智能

背景情况:

了解人类的意图对于机器人来说至关重要,以便在人机交互 (HRI) 中将任务与用户偏好保持一致.
基于语言纠正的传统轨迹修改方法需要广泛的培训,并难以在各种场景中进行概括.
现有的方法往往依赖于端到端的学习,限制了适应性,需要大量的预训练数据集.

研究的目的:

介绍ExTraCT,一个模块化框架,用于修改使用自然语言输入的机器人轨迹和行为.
让机器人能够将语言纠正适应新任务,包括复杂的动作,而无需额外的端到端训练.
为HRI应用提供更易于解释和多功能解决方案.

主要方法:

ExTraCT将语言理解与轨迹修改分开,使用大型语言模型 (LLM) 进行语义匹配.
该框架将语言纠正映射到预定义的轨迹修改函数,用于机器人路径调整.
模块化设计允许适应各种对象,初始轨迹和配置.

主要成果:

模拟和使用物理机器人手臂的用户研究表明,ExTraCT校正在80%的病例中是首选的.
该系统的准确性比基线方法有所改善.
在复杂的场景中,如辅助养,ExTraCT证明是有效的.

结论:

ExTraCT提供了一种多功能且易于解释的方法来解释HRI中的语言纠正.
模块化框架克服了传统方法的局限性,在各种应用中提供了适应性.
这项技术有助于机器人学习人类的偏好,并改善任务对齐.

关键词:

有助于机器人的机器人基础模型基础模型人与机器人的交互机器人技术中的语言大型语言模型.自然语言处理自然语言处理.

更多相关视频

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...