CAREER: Automated Design of Decentralized Robust and Explainable Swarm Systems (ADDRESS)

职业:去中心化、鲁棒性和可解释群系统的自动化设计(地址)

基本信息

  • 批准号:
    2048020
  • 负责人:
  • 金额:
    $ 50万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-06-01 至 2026-05-31
  • 项目状态:
    未结题

项目摘要

The objective of this Faculty Early Career Development (CAREER) project is to identify and test new scientific principles to design swarm robotic systems with dependable collective behavior. Motivated by observations of phenomenal cooperative behavior in nature, large teams of simple robots promise unprecedented task efficiency and resilience benefits over sophisticated standalone systems. These beneficial capabilities are fundamental to the future of disaster response, environment monitoring, military operations and space exploration, and to the continuing scientific leadership of the U.S. in these domains. However, most existing approaches to designing the behavior of mobile robots that operate as large collectives suffer from two key limitations: the lack of predictable performance guarantees at the swarm level and the inability to adapt to different uncertain environments and scales of operation. This award supports theoretical research to concurrently tackle these limitations by leveraging machine learning tools combined with rigorous engineering design approaches that enable systematic analysis and tailoring of how knowledge representation and the physical design of individual robots influence their collective behavior. These theoretical contributions will be reduced to practice by designing and testing new small aerial and ground robots for swarm applications with broad societal impact in the areas of time-critical emergency response and pollution clean-up. Outreach efforts engaging local emergency-response stakeholders will allow understanding of potential barriers to transitioning such swarm-robotic technologies to practice. This multidisciplinary project will also enable novel experiential learning environments and diversity initiatives for engineering students at the intersecting fields of design and robotics, and facilitate advanced skill development in these fields by enriching the graduate curricula and organizing a new workshop at a flagship Robotics conference.The overarching goal of this research is to investigate the central hypothesis that dependable swarm systems can be computationally designed via imitation learning of individual agent behavior from provably-optimal expert solutions and concurrent tailoring of agent morphology. Here "dependability" encompasses the generalizability, scalability and mathematical explainability of the ensuing collective behavior, which will be analyzed in the context of decentralized swarm robotic systems, comprising palm-sized wheeled robots and multirotor drones, that are tasked to provide target search and collective transport operations. To accomplish this goal, the following three key fundamental contributions are envisioned in this research: 1) develop learnable scale-agnostic representations of the individual agent's knowledge that regulates its task-planning processes embodied by novel Bayesian search and graph-theoretic models; 2) identify hybrid imitation learning approaches for adapting the individual agent behavior over varying environments, while minimizing the deviation of the ensuing collective behavior from provably-optimal offline solutions; 3) develop computational methods based on novel constrained policy gradient and co-evolution approaches to concurrently design agent morphology along with the learning of agent behavior, such that the ensuing morphological complexity optimally facilitates the necessary behavioral adaptations. These contributions will provide an increased understanding of "dependability" and the "interplay of form and behavior" that is expected to impact a broad range of multi-agent and decentralized systems beyond swarm robotics, such as various cyber physical systems. The integrated education plan involves the creation of 1) new experiential learning programs for engineering students, including underrepresented minorities, based on swarm computer games and conservation-focused drone flight experiments, and 2) a new graduate course and conference workshops.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.
这个教师早期职业发展(Career)项目的目标是确定和测试新的科学原理,以设计具有可靠集体行为的群体机器人系统。由于观察到自然界中现象级的合作行为,由简单机器人组成的大型团队比复杂的独立系统具有前所未有的任务效率和弹性优势。这些有益的能力对未来的灾难响应、环境监测、军事行动和太空探索以及美国在这些领域的持续科学领导地位至关重要。然而,大多数现有的设计移动机器人行为的方法都存在两个关键的局限性:在群体层面缺乏可预测的性能保证,以及无法适应不同的不确定环境和操作规模。该奖项支持理论研究,通过利用机器学习工具与严格的工程设计方法相结合,可以系统地分析和剪裁单个机器人的知识表示和物理设计如何影响它们的集体行为,同时解决这些限制。通过设计和测试新的小型空中和地面机器人,将这些理论贡献转化为实践,用于在时间紧迫的应急响应和污染清理领域具有广泛社会影响的群体应用。与当地应急响应利益相关者进行的外联工作将使人们了解将这种群体机器人技术转化为实践的潜在障碍。这个多学科项目还将为设计和机器人交叉领域的工程学生提供新颖的体验式学习环境和多样性倡议,并通过丰富研究生课程和在旗舰机器人会议上组织新的研讨会来促进这些领域的高级技能发展。本研究的总体目标是研究可靠的群体系统可以通过从可证明的最优专家解决方案中模仿学习个体代理行为和并发定制代理形态来计算设计的中心假设。这里的“可靠性”包括随后的集体行为的通用性、可扩展性和数学可解释性,将在分散的群体机器人系统的背景下进行分析,包括手掌大小的轮式机器人和多旋翼无人机,其任务是提供目标搜索和集体运输操作。为了实现这一目标,本研究设想了以下三个关键的基本贡献:1)开发可学习的个体智能体知识的尺度不可知表示,该表示调节其任务规划过程,具体体现在新的贝叶斯搜索和图论模型中;2)识别混合模仿学习方法,以适应不同环境下个体智能体的行为,同时最小化随后的集体行为与可证明的最优离线解决方案的偏差;3)发展基于新型约束策略梯度和协同进化方法的计算方法,在学习智能体行为的同时设计智能体形态,使形态复杂度最优地促进必要的行为适应。这些贡献将增加对“可靠性”和“形式与行为的相互作用”的理解,预计将影响群机器人之外的广泛的多代理和分散系统,例如各种网络物理系统。综合教育计划包括:1)基于群体电脑游戏和以保护为重点的无人机飞行实验,为工程专业学生(包括少数族裔)创建新的体验式学习项目;2)新的研究生课程和会议研讨会。该奖项反映了美国国家科学基金会的法定使命,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(9)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Efficient Planning of Multi-Robot Collective Transport using Graph Reinforcement Learning with Higher Order Topological Abstraction
Graph Learning Based Decision Support for Multi-Aircraft Take-Off and Landing at Urban Air Mobility Vertiports
  • DOI:
    10.2514/6.2023-1848
  • 发表时间:
    2023-01
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Prajit K. Kumar;Jhoel Witter;Steve Paul;Karthik Dantu;Souma Chowdhury
  • 通讯作者:
    Prajit K. Kumar;Jhoel Witter;Steve Paul;Karthik Dantu;Souma Chowdhury
Adaptive Neuroevolution With Genetic Operator Control and Two-Way Complexity Variation
  • DOI:
    10.1109/tai.2022.3214181
  • 发表时间:
    2023-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    A. Behjat;Nathan Maurer;Sharat Chidambaran;Souma Chowdhury
  • 通讯作者:
    A. Behjat;Nathan Maurer;Sharat Chidambaran;Souma Chowdhury
A penalized batch-Bayesian approach to informative path planning for decentralized swarm robotic search
  • DOI:
    10.1007/s10514-022-10047-8
  • 发表时间:
    2022-06
  • 期刊:
  • 影响因子:
    3.5
  • 作者:
    P. Ghassemi;Mark Balazon;Souma Chowdhury
  • 通讯作者:
    P. Ghassemi;Mark Balazon;Souma Chowdhury
Framework for Analyzing Human Cognition in Operationally-Relevant Human Swarm Interaction
与操作相关的人群交互中的人类认知分析框架
{{ 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 }}

Souma Chowdhury其他文献

Comprehensive Product Platform Planning (CP3) Using Mixed-Discrete Particle Swarm Optimization and a New Commonality Index
使用混合离散粒子群优化和新的共性指数的综合产品平台规划 (CP3)
  • DOI:
    10.1115/detc2012-70954
  • 发表时间:
    2012
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Souma Chowdhury;A. Messac;Ritesh A. Khire
  • 通讯作者:
    Ritesh A. Khire
Distribution Network Restoration: Resource Scheduling Considering Coupled Transportation-Power Networks
配电网恢复:考虑耦合运输-电力网络的资源调度
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Harshal D. Kaushik;R. Jacob;Souma Chowdhury;Jie Zhang
  • 通讯作者:
    Jie Zhang
Large-aperture experimental characterization of the acoustic field generated by a hovering unmanned aerial vehicle.
悬停无人机产生的声场的大孔径实验表征。
One-Step Continuous Product Platform Planning: Methods and Applications
一步式连续产品平台规划:方法与应用
  • DOI:
    10.1007/978-1-4614-7937-6_12
  • 发表时间:
    2014
  • 期刊:
  • 影响因子:
    0
  • 作者:
    A. Messac;Souma Chowdhury;Ritesh A. Khire
  • 通讯作者:
    Ritesh A. Khire
Domain Segmentation based on Uncertainty in the Surrogate (DSUS)
基于代理不确定性的域分割 (DSUS)
  • DOI:
    10.2514/6.2012-1929
  • 发表时间:
    2012
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jie Zhang;Souma Chowdhury;A. Messac
  • 通讯作者:
    A. Messac

Souma Chowdhury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('Souma Chowdhury', 18)}}的其他基金

System of Systems Approach and Uncertainty Mitigation/Exploitation for Wind Farm Design
风电场设计的系统方法和不确定性缓解/利用的系统
  • 批准号:
    1642340
  • 财政年份:
    2016
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
System of Systems Approach and Uncertainty Mitigation/Exploitation for Wind Farm Design
风电场设计的系统方法和不确定性缓解/利用的系统
  • 批准号:
    1437746
  • 财政年份:
    2013
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant

相似海外基金

RII Track-4:NSF: Automated Design and Innovation of Chemical Production Processes with Intelligent Computing
RII Track-4:NSF:利用智能计算进行化学品生产过程的自动化设计和创新
  • 批准号:
    2327303
  • 财政年份:
    2024
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: DMREF: AI-enabled Automated design of ultrastrong and ultraelastic metallic alloys
合作研究:DMREF:基于人工智能的超强和超弹性金属合金的自动化设计
  • 批准号:
    2411603
  • 财政年份:
    2024
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
CAREER: Learning and Leveraging Conventions in the Design of an Adaptive Haptic Shared Control for Steering a Semi-Automated Vehicle
职业:学习和利用设计用于驾驶半自动车辆的自适应触觉共享控制的惯例
  • 批准号:
    2238268
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
LEAP-HI: Automated Design for 3D Printing of Microfluidic Devices for Healthcare Applications
LEAP-HI:医疗保健应用微流控设备 3D 打印的自动化设计
  • 批准号:
    2245494
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
Equipment: MRI: Track 2 Acquisition of an Automated High-Throughput System for Combinatorial Design and Development of Complex Polymer Systems
设备: MRI:轨道 2 获取用于复杂聚合物系统的组合设计和开发的自动化高通量系统
  • 批准号:
    2320276
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
DMREF/Collaborative Research: Accelerated Discovery of Sustainable Bioplastics: Automated, Tunable, Integrated Design, Processing and Modeling
DMREF/合作研究:加速可持续生物塑料的发现:自动化、可调、集成设计、加工和建模
  • 批准号:
    2323976
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: DMREF: AI-enabled Automated design of ultrastrong and ultraelastic metallic alloys
合作研究:DMREF:基于人工智能的超强和超弹性金属合金的自动化设计
  • 批准号:
    2323767
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
DMREF/Collaborative Research: Accelerated Discovery of Sustainable Bioplastics: Automated, Tunable, Integrated Design, Processing and Modeling
DMREF/合作研究:加速可持续生物塑料的发现:自动化、可调、集成设计、加工和建模
  • 批准号:
    2323977
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: DMREF: AI-enabled Automated design of ultrastrong and ultraelastic metallic alloys
合作研究:DMREF:基于人工智能的超强和超弹性金属合金的自动化设计
  • 批准号:
    2323765
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: DMREF: AI-enabled Automated design of ultrastrong and ultraelastic metallic alloys
合作研究:DMREF:基于人工智能的超强和超弹性金属合金的自动化设计
  • 批准号:
    2323766
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了