EAPSI: Multimodal Interaction Algorithm for Human-Robot Interaction with Biologically-Inspired Robots

EAPSI:仿生机器人人机交互的多模态交互算法

基本信息

  • 批准号:
    1714060
  • 负责人:
  • 金额:
    $ 0.54万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Fellowship Award
  • 财政年份:
    2017
  • 资助国家:
    美国
  • 起止时间:
    2017-06-01 至 2018-05-31
  • 项目状态:
    已结题

项目摘要

In order for robots to engage in physical interactions with humans, their behavior needs to be intrinsically safe. Current state-of-the-art algorithms do so by maintaining an awareness of humans with single-modality data models, for example limb positions derived from a camera. However, approaches using only a single input modality typically neglect other potentially critical sources of information. In addition, they are prone to noise, failures, or line-sight problems, since no redundant data sources are available. This project will address this issue with the development of a machine learning algorithm which performs human intention inference and determines an appropriate robot response for human-robot interaction using multi-modal data sources, such as camera, accelerometer, shoe-based pressure sensor, and electromyography data. This research will be conducted in collaboration with Dr. Shuhei Ikemoto and Dr. Koh Hosoda at Osaka University, who specialize in biologically-inspired robotics and human-robot interaction. This project benefits from Dr. Ikemoto's and Dr. Hosoda's invaluable expertise, as well as access to a human-inspired, pneumatically-actuated robot located at Osaka University which will enable unique human-robot interaction scenarios that are not currently possible at the researcher's institution.Interaction Primitives are a state-of-the-art framework for modeling the interaction that takes place between a robot and a human during collaborative, physical activities. However, this existing framework is designed to work in low dimensional space with a single data modality for each agent. When introducing additional modalities in this project, the dimensionality of the input data will increase rapidly. At the same time, the number of training samples will remain constant, since that is physically constrained by the number of demonstrations that can be performed. To resolve this issue, this project will develop an extension of Interaction Primitives capable of performing density estimation with high dimension, low sample size data sets with the goal of producing safer, and more accurate interactions.This award under the East Asia and Pacific Summer Institutes program supports summer research by a U.S. graduate student and is jointly funded by NSF and the Japan Society for the Promotion of Science.
为了让机器人与人类进行物理交互,它们的行为需要本质安全。目前最先进的算法通过使用单模态数据模型(例如,从相机导出的肢体位置)来保持对人类的感知来实现。然而,仅使用单一输入模态的方法通常会忽略其他潜在的关键信息源。此外,由于没有冗余的数据源,它们容易出现噪声、故障或视线问题。该项目将通过开发一种机器学习算法来解决这个问题,该算法可以执行人类意图推断,并使用多模态数据源(如摄像头,加速度计,基于鞋的压力传感器和肌电图数据)确定适当的机器人响应以进行人机交互。这项研究将与大坂大学的Shuhei Ikemoto博士和Koh Hosoda博士合作进行,他们专门研究生物启发的机器人技术和人机交互。该项目得益于池本博士和细田博士的宝贵专业知识,以及大坂大学的一个人类启发的、自动驱动的机器人,该机器人将实现独特的人机交互场景,这在研究机构目前是不可能的。Interaction Primitives是一个最先进的框架,用于建模机器人和人类之间在协作过程中发生的交互,身体活动。然而,这个现有的框架被设计成在低维空间中工作,每个代理具有单个数据模态。当在这个项目中引入额外的模式时,输入数据的维度将迅速增加。与此同时,训练样本的数量将保持不变,因为这在物理上受到可以进行的演示数量的限制。为了解决这一问题,本项目将开发一个扩展的Interaction Primitives,能够对高维、低样本数据集进行密度估计,目标是产生更安全、更准确的交互。该奖项是由美国国家科学基金会(NSF)和日本科学促进会(Japan Society for the Promotion of Science)共同资助的东亚和太平洋夏季研究所(East Asia and Pacific Summer Institutes)项目下的一个奖项,旨在支持美国研究生的夏季研究。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Joseph Campbell其他文献

Pathways to Bliss: Mythology and Personal Transformation
通往幸福的途径:神话与个人转变
  • DOI:
  • 发表时间:
    2004
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Joseph Campbell;David Kudler
  • 通讯作者:
    David Kudler
Joseph Campbell and the Power of Myth. Program 5, Love and the Goddess: Transcript
约瑟夫·坎贝尔和神话的力量。
  • DOI:
  • 发表时间:
    1988
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Joseph Campbell
  • 通讯作者:
    Joseph Campbell
Multimodal Dataset of Human-Robot Hugging Interaction
人机拥抱交互的多模态数据集
  • DOI:
  • 发表时间:
    2019
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Kunal Bagewadi;Joseph Campbell;H. B. Amor
  • 通讯作者:
    H. B. Amor
The Art of Indian Asia.
印度亚洲艺术。
  • DOI:
    10.2307/2941899
  • 发表时间:
    1955
  • 期刊:
  • 影响因子:
    0.3
  • 作者:
    Stella Kramrisch;H. Zimmer;Joseph Campbell
  • 通讯作者:
    Joseph Campbell
LOST IN THE CLOTS: A CASE OF PRIMARY PULMONARY ARTERY SARCOMA MASQUERADING AS A PULMONARY EMBOLISM
  • DOI:
    10.1016/s0735-1097(24)04772-7
  • 发表时间:
    2024-04-02
  • 期刊:
  • 影响因子:
  • 作者:
    Sarah Grebennikov;Michael Jolly;Joseph Campbell;Mitchell J. Silver
  • 通讯作者:
    Mitchell J. Silver

Joseph Campbell的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Joseph Campbell', 18)}}的其他基金

HR Line of Business (HRLOB)
人力资源业务线 (HRLOB)
  • 批准号:
    2133209
  • 财政年份:
    2021
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
HR LoB
人力资源LOB
  • 批准号:
    2039835
  • 财政年份:
    2020
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
FY 20 HRLoB
20 财年 HRLoB
  • 批准号:
    1950045
  • 财政年份:
    2019
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
HRLOB
HRLOB
  • 批准号:
    1842283
  • 财政年份:
    2018
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
Human Resource Line of Business (HRLOB) FY 2017
2017 财年人力资源业务线 (HRLOB)
  • 批准号:
    1749043
  • 财政年份:
    2017
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
HR Line Of Business
人力资源业务线
  • 批准号:
    1543896
  • 财政年份:
    2015
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
EAPSI: Object Recognition for the Purpose of Traffic Compliance of Autonomous Vehicles
EAPSI:用于自动驾驶车辆交通合规性的物体识别
  • 批准号:
    1515589
  • 财政年份:
    2015
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Fellowship Award
2013 Human Resurces Line of Business Services
2013 人力资源业务线服务
  • 批准号:
    1344057
  • 财政年份:
    2013
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
Service Administering The Employee Viewpoint Survey for FY13
2013 财年员工观点调查管理服务
  • 批准号:
    1341109
  • 财政年份:
    2013
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement
FY12 Federal Human Resource Line of Business (HR LoB)
2012 财年联邦人力资源业务线 (HR LoB)
  • 批准号:
    1240302
  • 财政年份:
    2012
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Contract Interagency Agreement

相似海外基金

Intersubjective AI-driven multimodal interaction for advanced user-centric human robot collaborative applications (Jarvis)
主体间人工智能驱动的多模式交互,用于以用户为中心的高级人类机器人协作应用程序 (Jarvis)
  • 批准号:
    10099311
  • 财政年份:
    2024
  • 资助金额:
    $ 0.54万
  • 项目类别:
    EU-Funded
Multimodal conversation analysis of Japanese Noh classroom practice: Focusing on the interaction of teaching and learning
日本能剧课堂实践的多模态会话分析:关注教与学的互动
  • 批准号:
    23K12191
  • 财政年份:
    2023
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
CAREER: HCC: Microgesture and Multimodal Interaction Techniques for Augmented Reality
职业:HCC:增强现实的微手势和多模态交互技术
  • 批准号:
    2238313
  • 财政年份:
    2023
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Continuing Grant
Development of a multimodal image recognition system for realizing natural interaction with mid-air images
开发多模态图像识别系统,实现与空中图像的自然交互
  • 批准号:
    23K11189
  • 财政年份:
    2023
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
SBIR Phase I: Overcoming interaction barriers in augmented reality via wearable multimodal sensing
SBIR 第一阶段:通过可穿戴多模态传感克服增强现实中的交互障碍
  • 批准号:
    2322424
  • 财政年份:
    2023
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Standard Grant
ERI: High-performance Human-robot Collaborative Manufacturing Enabled by Integrated Multimodal Teaching, Learning, Prediction and Interaction
ERI:通过集成多模态教学、学习、预测和交互实现高性能人机协作制造
  • 批准号:
    2138351
  • 财政年份:
    2022
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Standard Grant
Multimodal measures of the interaction between cognition and language experience
认知与语言体验之间相互作用的多模态测量
  • 批准号:
    RGPIN-2022-04070
  • 财政年份:
    2022
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Discovery Grants Program - Individual
Enabling rich, open-ended human-robot interaction through robust, advanced multimodal perceptual capabilities for high-level reasoning
通过强大、先进的多模态感知能力进行高级推理,实现丰富、开放式的人机交互
  • 批准号:
    RGPIN-2019-06047
  • 财政年份:
    2022
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Discovery Grants Program - Individual
Emergent Reality: Knowledge Formation from Multimodal Learning through Human-Robot Interaction in Extended Reality
涌现现实:扩展现实中通过人机交互进行多模态学习的知识形成
  • 批准号:
    22K17981
  • 财政年份:
    2022
  • 资助金额:
    $ 0.54万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Interpretable Machine Learning for Multimodal Group Interaction
用于多模式群体交互的可解释机器学习
  • 批准号:
    572038-2022
  • 财政年份:
    2022
  • 资助金额:
    $ 0.54万
  • 项目类别:
    University Undergraduate Student Research Awards
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了