CAREER: Enhancing Robot Physical Intelligence via Crowdsourced Surrogate Learning
职业:通过众包代理学习增强机器人物理智能
基本信息
- 批准号:1944069
- 负责人:
- 金额:$ 56.37万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2020
- 资助国家:美国
- 起止时间:2020-08-15 至 2025-07-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
This Faculty Early Career Development (CAREER) grant develops a novel way to enhance skilled manipulation of objects as performed by human and robotic hands. Challenges associated with dexterous object manipulation have been a bottleneck limiting the application of robots in many production and service applications. This project introduces a novel chopsticks-like robot and associated methods that will allow robots to gradually develop "physical intelligence" (skills that can be transferred to novel situations) by learning from a large group of people, who are distributed across physical location and time. The project uses "crowdsourcing" to obtain a large set of data from people using the chopsticks robot to guide a similar, remote robot through industrial and social activities. Sensorimotor control signals observed during teleoperation are parsed by a novel artificial intelligence controller to improve autonomous robot skills. An interesting feature of this controller is its ability to compose new object manipulation skills from parts of previously observed skills. The project develops a user training method that leverages the robot's acquired physical intelligence to actively guide and improve robot teleoperation skills of humans. The innovations promise to advance the national health, prosperity and welfare by improving dexterity of robotic and human manipulation skills in a variety of applications, including manufacturing, medical surgery, and home assistance. The project includes an educational component that engages pre-college and college-age students from diverse backgrounds.This project will develop and test a novel focus on improving dexterous object manipulation skills performed by human and robotic hands. The project advances three novel ideas. First, the PI will use Amazon Mechanical Turk to implement a teleoperation system (user interface, user management system, and robot learning database) linking a group of human operators with remote robots. This approach, called "Crowdsourced Surrogate Learning" (CSL), builds a database of sensor, motor, and machine vision data collected while a large number of people separately use a novel chopsticks-like robot to teleoperate a similar robot to conduct industrial and social tasks. These human subjects experiments will provide the data needed for subsequent robot skill learning and generalization using an approach called "Robot Composite Learning" (RCL). RCL implements a discretized joint state space of the robot and the object being grasped/manipulated, along with a statistical inference technique, to compose new command signals - in real-time - enabling the two-fingered robot hand to learn never-demonstrated skills such as new, in-hand manipulations of small items. Finally, the PI will develop a "Reciprocal Skill Induction" method that enables the CSL/RCL system to actively guide and improve the robot teleoperation skills of humans by providing haptic guidance using "virtual fixtures" that fade as a novel skill is learned.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
该学院早期职业发展(CAREER)资助开发了一种新的方法,以提高人类和机器人手对物体的熟练操作。与灵巧物体操作相关的挑战一直是限制机器人在许多生产和服务应用中应用的瓶颈。该项目介绍了一种新型的筷子状机器人和相关方法,该方法将允许机器人通过向分布在物理位置和时间上的一大群人学习来逐渐发展“物理智能”(可以转移到新情况下的技能)。该项目使用“众包”从使用筷子机器人的人那里获得大量数据,以指导类似的远程机器人进行工业和社会活动。在遥操作过程中观察到的感觉运动控制信号解析的一种新的人工智能控制器,以提高自主机器人的技能。这个控制器的一个有趣的功能是它能够从以前观察到的技能组成新的对象操作技能。该项目开发了一种用户训练方法,利用机器人获得的物理智能来主动引导和提高人类的机器人遥操作技能。这些创新有望通过提高机器人和人类操作技能在各种应用中的灵活性来促进国民健康,繁荣和福利,包括制造,医疗手术和家庭援助。该项目包括一个教育部分,吸引来自不同背景的大学预科和大学年龄的学生。该项目将开发和测试一个新的重点,提高人类和机器人手执行的灵巧物体操作技能。该项目提出了三个新颖的想法。 首先,PI将使用Amazon Mechanical Turk实现远程操作系统(用户界面、用户管理系统和机器人学习数据库),将一组人类操作员与远程机器人连接起来。这种方法被称为“众包代理学习”(CSL),它建立了一个传感器、电机和机器视觉数据的数据库,而大量的人分别使用一种新型的筷子状机器人来远程操作类似的机器人来执行工业和社会任务。这些人类受试者实验将提供后续机器人技能学习和推广所需的数据,使用一种称为“机器人复合学习”(RCL)的方法。RCL实现了一个离散化的关节状态空间的机器人和物体被抓住/操纵,沿着的统计推断技术,组成新的命令信号-实时-使两指机器人手学习从未展示过的技能,如新的,在手的小物品的操作。最后,PI将开发一种“互惠技能诱导”方法,使CSL/RCL系统能够通过使用“虚拟夹具”提供触觉引导来主动引导和提高人类的机器人遥操作技能,该虚拟夹具会随着新技能的学习而消失。该奖项反映了NSF的法定使命,并通过使用基金会的智力价值和更广泛的影响审查标准进行评估而被认为值得支持。
项目成果
期刊论文数量(4)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Handling crowdsourced data using state space discretization for robot learning and synthesizing physical skills
- DOI:10.1007/s41315-020-00152-1
- 发表时间:2020-11
- 期刊:
- 影响因子:1.7
- 作者:Leidi Zhao;Lu Lu-Lu;Cong Wang
- 通讯作者:Leidi Zhao;Lu Lu-Lu;Cong Wang
Data-Oriented State Space Discretization for Crowdsourced Robot Learning of Physical Skills
- DOI:10.1115/1.4047961
- 发表时间:2021-04
- 期刊:
- 影响因子:0
- 作者:Leidi Zhao;Lu Lu-Lu;Cong Wang
- 通讯作者:Leidi Zhao;Lu Lu-Lu;Cong Wang
Two-finger Multi-DOF Folding Robot Grippers*
两指多自由度折叠机器人夹具*
- DOI:10.1016/j.ifacol.2022.10.491
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Samuels, Maxwell;Lu, Lu;Wang, Cong
- 通讯作者:Wang, Cong
A Survey Study on the Technology and Public Acceptance of Remote Labor*
- DOI:10.1016/j.ifacol.2022.10.548
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:M. Nicol;Lu Lu-Lu;Cong Wang
- 通讯作者:M. Nicol;Lu Lu-Lu;Cong Wang
{{
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 }}
Cong Wang其他文献
Traditional two-dimendional mesenchymal stem cells (MSCs) are better than spheroid MSCs on promoting retinal ganglion cells survival and axon regeneration
传统二维间充质干细胞(MSCs)在促进视网膜神经节细胞存活和轴突再生方面优于球状MSCs
- DOI:
- 发表时间:
2019 - 期刊:
- 影响因子:3.4
- 作者:
Wei Huang;Cong Wang;Lili Xie;Xiaoling Wang;Lusi Zhang;Changzheng Chen;Bing Jiang - 通讯作者:
Bing Jiang
The evolution of magnetic transitions, negative thermal expansion and unusual electronic transport properties in Mn3AgxMnyN
Mn3AgxMnyN 中磁转变、负热膨胀和异常电子传输特性的演变
- DOI:
10.1016/j.ssc.2015.08.024 - 发表时间:
2015-11 - 期刊:
- 影响因子:2.1
- 作者:
Lei Wang;Pengwei Hu;Muhammad Imran Malik;Cong Wang - 通讯作者:
Cong Wang
Giant zero-field cooling exchange-bias-like behavior in antiperovskite Mn3Co0.61Mn0.39N compound
反钙钛矿Mn3Co0.61Mn0.39N化合物中的巨大零场冷却交换偏置行为
- DOI:
10.1103/physrevmaterials.3.024409 - 发表时间:
2019 - 期刊:
- 影响因子:3.4
- 作者:
Ying Sun;Pengwei Hu;Kewen Shi;Hui Wu;Sihao Deng;Qingzhen Huang;Zhiyong Mao;Ping Song;Lei Wang;Weichang Hao;Shenghua Deng;Cong Wang - 通讯作者:
Cong Wang
Genome-wide interaction target profiling reveals a novel Peblr20-eRNA activation pathway to control stem cell pluripotency
全基因组相互作用靶标分析揭示了一种控制干细胞多能性的新型 Peblr20-eRNA 激活途径。
- DOI:
10.7150/thno.39093 - 发表时间:
2020 - 期刊:
- 影响因子:12.4
- 作者:
Cong Wang;Lin Jia;Yichen Wang;Zhonghua Du;Lei Zhou;Xue Wen;Hui Li;Shilin Zhang;Huiling Chen;Naifei Chen;Jingcheng Chen;Yanbo Zhu;Yuanyuan Nie;Ilkay Celic;Sujun Gao;Songling Zhang;Andrew R.Hoffman;Wei Li;Ji-Fan Hu;Jiuwei Cui - 通讯作者:
Jiuwei Cui
Neural learning control for discrete-time nonlinear systems in pure-feedback form
纯反馈形式离散时间非线性系统的神经学习控制
- DOI:
10.1007/s11432-020-3138-7 - 发表时间:
2022-01 - 期刊:
- 影响因子:0
- 作者:
Min Wang;Haotian Shi;Cong Wang;Jun Fu - 通讯作者:
Jun Fu
Cong Wang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('Cong Wang', 18)}}的其他基金
CAREER: Memory-Efficient, Heterogeneity-Aware and Robust Architecture for Federated Intelligence on Edge Devices
职业:边缘设备上联邦智能的内存高效、异构感知和鲁棒架构
- 批准号:
2152580 - 财政年份:2021
- 资助金额:
$ 56.37万 - 项目类别:
Continuing Grant
CAREER: Memory-Efficient, Heterogeneity-Aware and Robust Architecture for Federated Intelligence on Edge Devices
职业:边缘设备上联邦智能的内存高效、异构感知和鲁棒架构
- 批准号:
2044841 - 财政年份:2021
- 资助金额:
$ 56.37万 - 项目类别:
Continuing Grant
CRII: SHF Software and Hardware Architecture Co-Design for Deep Learning on Mobile Device
CRII:移动设备深度学习的SHF软硬件架构协同设计
- 批准号:
1850045 - 财政年份:2019
- 资助金额:
$ 56.37万 - 项目类别:
Standard Grant
STTR Phase I: Plasmonic Carbon dioxide to fuel photocatalysis by solar energy
STTR 第一阶段:等离子体二氧化碳通过太阳能为光催化提供燃料
- 批准号:
1549710 - 财政年份:2016
- 资助金额:
$ 56.37万 - 项目类别:
Standard Grant
相似海外基金
NRI: Enhancing Autonomous Underwater Robot Perception for Aquatic Species Management
NRI:增强自主水下机器人感知以进行水生物种管理
- 批准号:
2220956 - 财政年份:2023
- 资助金额:
$ 56.37万 - 项目类别:
Standard Grant
Enhancing User Experience with Partner Robot
与合作伙伴机器人增强用户体验
- 批准号:
23K13286 - 财政年份:2023
- 资助金额:
$ 56.37万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
CAREER: Enhancing the Robustness of Human-Robot Interactions via Automatic Scenario Generation
职业:通过自动场景生成增强人机交互的鲁棒性
- 批准号:
2145077 - 财政年份:2022
- 资助金额:
$ 56.37万 - 项目类别:
Continuing Grant
Self-Locomotive Antimicrobial Micro-Robot (SLAM) Enhancing Biofilm-Infected Wound Healing
自移动抗菌微型机器人 (SLAM) 增强生物膜感染伤口愈合
- 批准号:
10366359 - 财政年份:2022
- 资助金额:
$ 56.37万 - 项目类别:
Self-Locomotive Antimicrobial Micro-Robot (SLAM) Enhancing Biofilm-Infected Wound Healing
自移动抗菌微型机器人 (SLAM) 增强生物膜感染伤口愈合
- 批准号:
10612835 - 财政年份:2022
- 资助金额:
$ 56.37万 - 项目类别:
Enhancing Student Curiosity using Robot-Embodied Conversational Agents
使用机器人会话代理增强学生的好奇心
- 批准号:
534987-2019 - 财政年份:2020
- 资助金额:
$ 56.37万 - 项目类别:
Postgraduate Scholarships - Doctoral
FW-HTF-RM: Enhancing Future Work of Nursing Professionals through Collaborative Human-Robot Interfaces
FW-HTF-RM:通过协作式人机界面增强护理专业人员的未来工作
- 批准号:
2026584 - 财政年份:2020
- 资助金额:
$ 56.37万 - 项目类别:
Standard Grant
Design of Deep Neural Networks for Enhancing Robot Performance
提高机器人性能的深度神经网络设计
- 批准号:
518841-2018 - 财政年份:2020
- 资助金额:
$ 56.37万 - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
Design of Deep Neural Networks for Enhancing Robot Performance
提高机器人性能的深度神经网络设计
- 批准号:
518841-2018 - 财政年份:2019
- 资助金额:
$ 56.37万 - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
FW-HTF-P: Human-Robot Collaboration for Enhancing Work Capabilities
FW-HTF-P:人机协作增强工作能力
- 批准号:
1928425 - 财政年份:2019
- 资助金额:
$ 56.37万 - 项目类别:
Standard Grant