Robots Teaching Robots: Real-time Optimal Control of Complex Engineering Systems

机器人教学机器人:复杂工程系统的实时优化控制

基本信息

  • 批准号:
    2029181
  • 负责人:
  • 金额:
    $ 47.99万
  • 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:
    2020-10-01 至 2024-07-31
  • 项目状态:
    已结题

项目摘要

This project introduces learner-helper robot pairs to enable the learner robot to use physical experimentation to improve its performance on repetitive task, without accurate analytical or numerical models. The specific challenge is that these tasks -- for example walking on two legs or riding a bicycle -- require a minimal necessary level of performance, below which the robot is unable to function. In the examples, this minimal level of ability corresponds to not falling over. The helper satisfies these minimal requirements while the learner uses repeated trials to improve its performance. For example, the helper might suspend the two-legged walker from a traveling harness or move alongside the bicycle robot providing an additional point of support. As the learner-helper team masters the task, the amount of assistance that the helper can apply is gradually reduced, until the learner is performing at a high level on its own. An analogy is a child learning to ride a bike with the help of an adult moving alongside. The new control technique will enable robots to teach robots in training lines of future factories similar to robots currently used in assembly lines of manufacturing companies. Therefore, the results of this research will benefit the U.S. economy and society. This research also involves several disciplines including mechanical, electrical, computer, and control engineering. The multi-disciplinary approach is expected to broaden the participation of underrepresented groups in research and positively impact engineering education.Optimal control is a branch of control theory that has the potential to revolutionize the creation of intelligent engineering systems, industrial robots, surgical robots, and assistive robots that can improve by repeated experience, somewhat similar to humans. There are many optimal control techniques to control engineering systems. However, almost all currently available techniques require high-fidelity models or a large amount of measured data to mitigate the so-called simulation-reality gap; the gap between the optimal performance predicted by computer simulations and the non-optimal performance observed in real engineering applications. This award supports fundamental research to close the simulation-reality gap when optimal control is applied to engineering systems. Model-based optimal control techniques enable efficient computation but they are subject to conservative control performance. Data-driven optimal control techniques mitigate the detrimental effect of uncertain models, but to do so, they require a large amount of training data. Therefore, scientific barriers must be overcome to realize the full application potential of optimal control techniques. This research will address the knowledge gap that limits the potential and theoretical promise of optimal control theory when applied to complex engineering systems. The new technique promotes optimization of system performance via real-time experiments guided by dedicated teacher robots, instead of optimizing system performance guided only by uncertain model-based predictions and measured data. The technique delivers a transformative approach to control the class of complex, underactuated, and unstable robots, for which obtaining high-fidelity models is challenging, while gathering training data is time-consuming. The research outcomes could potentially provide mainstream paradigms in creating next-generation intelligent machines.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.
本计画引进学习者-助手机器人配对,使学习机器人在没有精确解析或数值模型的情况下,能够使用物理实验来改善其重复性任务的表现。具体的挑战是,这些任务-例如用两条腿走路或骑自行车-需要最低的必要性能水平,低于该水平,机器人无法正常工作。在示例中,该最低能力水平对应于不跌倒。帮助者满足这些最低要求,而学习者使用重复的试验来提高其性能。例如,助手可以将两条腿的步行者悬挂在行进安全带上,或者沿着自行车机器人移动,从而提供额外的支撑点。随着学习者-帮助者团队掌握了任务,帮助者可以应用的帮助量逐渐减少,直到学习者自己表现出高水平。一个类比是一个孩子在一个成年人的帮助下学习骑自行车。新的控制技术将使机器人能够在未来工厂的培训线上教授机器人,类似于目前在制造公司的装配线上使用的机器人。因此,这项研究的成果将有利于美国的经济和社会。这项研究还涉及多个学科,包括机械,电气,计算机和控制工程。最优控制是控制理论的一个分支,它有可能为智能工程系统、工业机器人、手术机器人和辅助机器人的创造带来革命性的变化,这些机器人可以通过重复的经验来改进,有点类似于人类。有许多最优控制技术来控制工程系统。然而,几乎所有当前可用的技术都需要高保真度模型或大量测量数据来缓解所谓的仿真-现实差距;由计算机仿真预测的最佳性能与在真实的工程应用中观察到的非最佳性能之间的差距。该奖项支持基础研究,以缩小最优控制应用于工程系统时的模拟-现实差距。基于模型的最优控制技术能够实现高效的计算,但它们受到保守的控制性能的影响。数据驱动的最优控制技术减轻了不确定模型的不利影响,但要做到这一点,它们需要大量的训练数据。因此,必须克服科学障碍,以实现最优控制技术的充分应用潜力。这项研究将解决知识差距,限制了最优控制理论的潜力和理论承诺时,应用于复杂的工程系统。新技术通过专用教师机器人指导的实时实验来优化系统性能,而不是仅通过基于不确定模型的预测和测量数据来优化系统性能。该技术提供了一种变革性的方法来控制复杂,欠驱动和不稳定的机器人,对于这些机器人来说,获得高保真模型是具有挑战性的,而收集训练数据是耗时的。该研究成果可能为创造下一代智能机器提供主流范例。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(1)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Data-Driven Iterative Optimal Control for Switched Dynamical Systems
切换动力系统的数据驱动迭代最优控制
  • DOI:
    10.1109/lra.2022.3226075
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    5.2
  • 作者:
    Chen, Yuqing;Li, Yangzhi;Braun, David J.
  • 通讯作者:
    Braun, David J.
{{ 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 }}

David Braun其他文献

An invariantist theory of ‘might’ might be right
“可能”的不变论可能是正确的
  • DOI:
  • 发表时间:
    2012
  • 期刊:
  • 影响因子:
    0
  • 作者:
    David Braun
  • 通讯作者:
    David Braun
Contextualism about ‘might’ and says-that ascriptions
关于“可能”的语境主义并说归因
  • DOI:
  • 发表时间:
    2013
  • 期刊:
  • 影响因子:
    0
  • 作者:
    David Braun
  • 通讯作者:
    David Braun
Structured characters and complex demonstratives
  • DOI:
    10.1007/bf00989803
  • 发表时间:
    1994-05-01
  • 期刊:
  • 影响因子:
    1.300
  • 作者:
    David Braun
  • 通讯作者:
    David Braun
Russellianism and Prediction
  • DOI:
    10.1023/a:1010387013995
  • 发表时间:
    2001-01-01
  • 期刊:
  • 影响因子:
    1.300
  • 作者:
    David Braun
  • 通讯作者:
    David Braun
Scott Soames. 2002. Beyond Rigidity: The Unfinished Semantic Agenda of Naming and Necessity.
  • DOI:
    10.1023/a:1024175605019
  • 发表时间:
    2003-01-01
  • 期刊:
  • 影响因子:
    1.300
  • 作者:
    David Braun
  • 通讯作者:
    David Braun

David Braun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('David Braun', 18)}}的其他基金

CAREER: Mechanically Adaptive, Energetically Passive Robotics
职业:机械自适应、能量被动机器人
  • 批准号:
    2144551
  • 财政年份:
    2022
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Collaborative Research: Examining Pyrotechnology and Ecosystem Change in the Archaeological Record
合作研究:检查考古记录中的火工技术和生态系统变化
  • 批准号:
    2018896
  • 财政年份:
    2020
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Collaborative Research: REU Site: Past and Present Human-Environment Dynamics
合作研究:REU 站点:过去和现在的人类环境动态
  • 批准号:
    1852441
  • 财政年份:
    2019
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Continuing Grant
Collaborative Research: Hominin diversity, paleobiology, and behavior at the terminal Pliocene
合作研究:上新世末期的古人类多样性、古生物学和行为
  • 批准号:
    1853355
  • 财政年份:
    2019
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Doctoral Dissertation Research: Movement Ecology and Hominin Behavioral Evolution
博士论文研究:运动生态学与人类行为进化
  • 批准号:
    1747943
  • 财政年份:
    2018
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Hominin footprints, fossils, and their context in the early Pleistocene of Koobi Fora, Kenya
肯尼亚库比福拉更新世早期的古人类足迹、化石及其背景
  • 批准号:
    1744150
  • 财政年份:
    2017
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Continuing Grant
Meeting: 58th Annual Maize Genetics Conference; Jacksonville, Florida; March 17-20, 2016
会议:第58届玉米遗传学年会;
  • 批准号:
    1608773
  • 财政年份:
    2016
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Technological Origins: Environmental and Behavioral Context of the Earliest Tool Users
技术起源:最早的工具用户的环境和行为背景
  • 批准号:
    1624398
  • 财政年份:
    2016
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Collaborative Research: Filling in a temporal gap in hominin evolution
合作研究:填补古人类进化的时间空白
  • 批准号:
    1460502
  • 财政年份:
    2015
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
U.S.-Kenya IRES: Origins of Human Adaptability
美国-肯尼亚 IRES:人类适应性的起源
  • 批准号:
    1358178
  • 财政年份:
    2014
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant

相似海外基金

Development of teaching materials on pneumatic control that can be remotely operated in real time
可远程实时操作的气动控制教材开发
  • 批准号:
    22K02852
  • 财政年份:
    2022
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Collaborative Research: Connecting Elementary Mathematics Teaching to Real-World Issues
合作研究:将基础数学教学与现实世界问题联系起来
  • 批准号:
    2101463
  • 财政年份:
    2021
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Continuing Grant
Collaborative Research: Connecting Elementary Mathematics Teaching to Real-World Issues
合作研究:将基础数学教学与现实世界问题联系起来
  • 批准号:
    2101456
  • 财政年份:
    2021
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Continuing Grant
Research on ICT teaching material production using real-time 3DCG
利用实时3DCG制作ICT教材的研究
  • 批准号:
    20K12105
  • 财政年份:
    2020
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Berry College MRI: Aquisition of a Flex Real-Time PCR System for Undergraduate Research and Teaching
贝里学院 MRI:为本科生研究和教学购置 Flex 实时 PCR 系统
  • 批准号:
    1828540
  • 财政年份:
    2018
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Development of curriculum and teaching materials to cultivate "reading literacy that function in real life and learning of various subjects"
开发课程及教材,培养“生活阅读素养、各科学习能力”
  • 批准号:
    17K04833
  • 财政年份:
    2017
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
MRI: Acquisition of a quantitative real-time gene expression monitoring system for undergraduate research and teaching at Pace University 2016
MRI:2016年佩斯大学采购用于本科生研究和教学的定量实时基因表达监测系统
  • 批准号:
    1625841
  • 财政年份:
    2016
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Standard Grant
Real-time body motion coding for skills teaching
用于技能教学的实时身体动作编码
  • 批准号:
    15K16257
  • 财政年份:
    2015
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Young Scientists (B)
Improvement of Teaching Practice by Real-Time Monitoring Method for Teachers
教师实时监控方法改进教学实践
  • 批准号:
    15K04253
  • 财政年份:
    2015
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Implementation and validation for quality evaluation model of web-based teaching materials using learning log collected in real time
基于实时采集学习日志的网络教材质量评价模型的实现与验证
  • 批准号:
    26330412
  • 财政年份:
    2014
  • 资助金额:
    $ 47.99万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了