FRR: Collaborative Research: Unsupervised Active Learning for Aquatic Robot Perception and Control
FRR:协作研究:用于水生机器人感知和控制的无监督主动学习
基本信息
- 批准号:2237576
- 负责人:
- 金额:$ 41.16万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-04-15 至 2026-03-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Rapid developments in machine learning and artificial intelligence in recent years have greatly advanced perception capabilities and thus the level of autonomy for machines, as evidenced by great strides made in autonomous vehicles and aerial drones over the last decade. These successes are due to advances in computing hardware and large datasets for training learning algorithms. However, for many real-world robotic applications, a robot’s environment may be so complex that no existing datasets are adequate, and synthetically generating high-fidelity data in simulation may not be possible. In such cases a robot will need to collect data in its real operating environment to learn. The robot will need to purposefully plan its motion and interaction with the environment to enable sensors to gather the most informative data. This award supports research to create algorithms for efficient robot active learning for perception and control of complex systems in highly dynamic and uncertain environments, such as the aquatic environment. Advances will have broad implications in applications of robotic technologies, such as aquatic debris cleanup, underwater search and rescue, and personalized minimally invasive robotic surgery. In particular, the team will collaborate with the United States Coast Guard and apply the developed algorithms to improve their search capacities. The goal of this project will be accomplished through the pursuit of three interconnected research thrusts: 1) active learning for building data-driven perception models with multi-sensory data; 2) active learning of models describing temporal evolution of perceptional features for control purposes, using data-driven operators to describe latent dynamics; and 3) experimental demonstration and evaluation with a running case study of autonomous aquatic debris removal using an unmanned surface vehicle equipped with soft sensor-rich robotic arms. This work will advance the fundamental understanding of design principles for learning-based perception models when multiple sensing modalities are involved. The project will moreover develop new theory for learning the evolution of latent features, including convergence guarantees and controllability analysis.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.
近年来,机器学习和人工智能的快速发展极大地提高了感知能力,从而提高了机器的自主水平,过去十年中自动驾驶汽车和空中无人机的巨大进步就是明证。这些成功是由于计算硬件的进步和用于训练学习算法的大型数据集。然而,对于许多现实世界的机器人应用来说,机器人的环境可能非常复杂,以至于没有足够的现有数据集,并且在模拟中合成高保真数据可能是不可能的。在这种情况下,机器人需要在真实的操作环境中收集数据来学习。机器人将需要有目的地规划其运动和与环境的互动,以使传感器能够收集最具信息量的数据。该奖项支持在高动态和不确定环境(如水生环境)中为复杂系统的感知和控制创建高效机器人主动学习算法的研究。这些进步将对机器人技术的应用产生广泛的影响,如水下碎片清理、水下搜索和救援,以及个性化的微创机器人手术。特别是,该小组将与美国海岸警卫队合作,并应用开发的算法来提高其搜索能力。该项目的目标将通过追求三个相互关联的研究重点来实现:1)利用多感官数据构建数据驱动的感知模型的主动学习;2)主动学习用于控制目的的描述感知特征时间演化的模型,使用数据驱动算子来描述潜在动力学;3)以搭载柔性传感机械臂的无人水面飞行器为例,进行了水下垃圾自主清除的实验论证与评估。当涉及多种传感模式时,这项工作将促进对基于学习的感知模型设计原则的基本理解。该项目还将发展新的理论来学习潜在特征的进化,包括收敛保证和可控性分析。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(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 }}
Todd Murphey其他文献
Fast Ergodic Search with Kernel Functions
使用核函数进行快速遍历搜索
- DOI:
10.48550/arxiv.2403.01536 - 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Muchen Sun;Ayush Gaggar;Peter Trautman;Todd Murphey - 通讯作者:
Todd Murphey
Mixed-Strategy Nash Equilibrium for Crowd Navigation
人群导航的混合策略纳什均衡
- DOI:
10.48550/arxiv.2403.01537 - 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Muchen Sun;Francesca Baldini;Peter Trautman;Todd Murphey - 通讯作者:
Todd Murphey
Todd Murphey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('Todd Murphey', 18)}}的其他基金
CPS: Medium: Information based Control of Cyber-Physical Systems operating in uncertain environments
CPS:中:在不确定环境中运行的信息物理系统的基于信息的控制
- 批准号:
1837515 - 财政年份:2018
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
RI: Small: Collaborative Research: Information-driven Autonomous Exploration in Uncertain Underwater Environments
RI:小型:协作研究:不确定水下环境中信息驱动的自主探索
- 批准号:
1717951 - 财政年份:2017
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Stability and Optimality Properties of Sequential Action Control for Nonlinear and Hybrid Systems
非线性和混合系统顺序动作控制的稳定性和最优性
- 批准号:
1662233 - 财政年份:2017
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
NRI: Task-Based Assistance for Software-Enabled Biomedical Devices
NRI:针对软件支持的生物医学设备的基于任务的援助
- 批准号:
1637764 - 财政年份:2016
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
NRI: Autonomous Synthesis of Haptic Languages
NRI:触觉语言的自主合成
- 批准号:
1426961 - 财政年份:2014
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: Ergodic Trajectories in Discrete Mechanics
协作研究:离散力学中的遍历轨迹
- 批准号:
1334609 - 财政年份:2013
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
CPS: Synergy: Collaborative Research: Mutually Stabilized Correction in Physical Demonstration
CPS:协同:协作研究:物理演示中的相互稳定校正
- 批准号:
1329891 - 财政年份:2013
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Physical Design and Feedback Control of Hybrid Mechanical Systems
混合机械系统的物理设计和反馈控制
- 批准号:
1200321 - 财政年份:2012
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
RI: Small: Hierarchical Planning, Estimation, and Control for Hybrid Mechanical Systems
RI:小型:混合机械系统的分层规划、估计和控制
- 批准号:
1018167 - 财政年份:2010
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
CAREER: Planning and Control for Overconstrained Mechanisms
职业:过度约束机制的规划和控制
- 批准号:
0951688 - 财政年份:2009
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
相似海外基金
Collaborative Research: REU Site: Earth and Planetary Science and Astrophysics REU at the American Museum of Natural History in Collaboration with the City University of New York
合作研究:REU 地点:地球与行星科学和天体物理学 REU 与纽约市立大学合作,位于美国自然历史博物馆
- 批准号:
2348998 - 财政年份:2025
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: REU Site: Earth and Planetary Science and Astrophysics REU at the American Museum of Natural History in Collaboration with the City University of New York
合作研究:REU 地点:地球与行星科学和天体物理学 REU 与纽约市立大学合作,位于美国自然历史博物馆
- 批准号:
2348999 - 财政年份:2025
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: Investigating Southern Ocean Sea Surface Temperatures and Freshening during the Late Pliocene and Pleistocene along the Antarctic Margin
合作研究:调查上新世晚期和更新世沿南极边缘的南大洋海面温度和新鲜度
- 批准号:
2313120 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: NSFDEB-NERC: Warming's silver lining? Thermal compensation at multiple levels of organization may promote stream ecosystem stability in response to drought
合作研究:NSFDEB-NERC:变暖的一线希望?
- 批准号:
2312706 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: Chain Transform Fault: Understanding the dynamic behavior of a slow-slipping oceanic transform system
合作研究:链变换断层:了解慢滑海洋变换系统的动态行为
- 批准号:
2318855 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Continuing Grant
Collaborative Research: Understanding Environmental and Ecological Controls on Carbon Export and Flux Attenuation near Bermuda
合作研究:了解百慕大附近碳输出和通量衰减的环境和生态控制
- 批准号:
2318940 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: Deciphering the mechanisms of marine nitrous oxide cycling using stable isotopes, molecular markers and in situ rates
合作研究:利用稳定同位素、分子标记和原位速率破译海洋一氧化二氮循环机制
- 批准号:
2319097 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: URoL:ASC: Determining the relationship between genes and ecosystem processes to improve biogeochemical models for nutrient management
合作研究:URoL:ASC:确定基因与生态系统过程之间的关系,以改进营养管理的生物地球化学模型
- 批准号:
2319123 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: Subduction Megathrust Rheology: The Combined Roles of On- and Off-Fault Processes in Controlling Fault Slip Behavior
合作研究:俯冲巨型逆断层流变学:断层上和断层外过程在控制断层滑动行为中的综合作用
- 批准号:
2319848 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant
Collaborative Research: CyberTraining: Pilot: PowerCyber: Computational Training for Power Engineering Researchers
协作研究:CyberTraining:试点:PowerCyber:电力工程研究人员的计算培训
- 批准号:
2319895 - 财政年份:2024
- 资助金额:
$ 41.16万 - 项目类别:
Standard Grant














{{item.name}}会员




