EAGER: Robust Data-Driven Robotic Manipulation via Bayesian Inference and Passivity-Based Control
EAGER:通过贝叶斯推理和基于被动的控制进行稳健的数据驱动机器人操作
基本信息
- 批准号:2330794
- 负责人:
- 金额:$ 26.22万
- 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:2023-08-01 至 2025-07-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Robots usually move objects by firmly holding on to them. Some tasks cannot be done this way, because the object may be delicate, or large relative to the robot's arm or hand. For example, we use firm holds when moving a closed book, but delicate finger motions when turning a page. Since the robot's "hand" may move relative to the object, the contact type between the robot, object, and environment can change during manipulation. Forces applied on the object create different motions when contact conditions are different. Conversely, different motions may lead to different contacts in the future. Planning computational methods can identify the right sequence of forces and contact conditions that could complete a task. Small errors that crop up during execution of planned motions would normally be reduced by taking corrective actions. However, these corrective actions often do not account for changing = contacts, and the errors instead are more critical due to unanticipated contacts, ultimately leading to failure on tasks. This EArly-concept Grant for Exploratory Research (EAGER) project will study techniques to create plans for robot motion that mitigate instead of amplify errors during execution of such tasks. Such manipulation tasks involving significant contact events can be found in robotic applications such as loading dishwashers, fetching hard-to-reach objects from cluttered cupboards, or moving furniture. The project team will study new data-driven methods to train robust motion controllers that are derived from Bayesian neural networks with special structure informed by robotics and control principles. To account for the contact-rich nature of the task, the network will consist of a mixture-of-experts, where each expert is either a controller or a storage function used to derive a passivity-based controller. A gating network chooses which controller to use given the input to the network. Bayesian networks will provide a distribution over motor commands given an input, allowing the motion controller to account for uncertainty. The project will proceed in three overlapping stages: The investigators will use tools from formal verification to synthesize controllers that provably locally stabilize contact-rich motion plans, and use these controllers to initialize a prior distribution for the weights of the Bayesian neural network using knowledge distillation. This initialized network will be trained from task-based rewards in an end-to-end manner using data from differentiable simulators, where the robot-object-environment system parameters are uncertain. The trained network will be tested in experiments involving a robot arm pushing a large box over step-like obstacles designed to require changes in contact conditions during manipulation. The project, if successful, will identify a controller synthesis paradigm that simultaneously overcomes the simulation-to-reality gap and the data-inefficiency plaguing purely data-driven approaches for contact-rich object manipulation. This project will also advance knowledge in scaling up computational controller synthesis, and contribute new tools for GPU-accelerated simulation of stochastic systems.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.
机器人通常通过牢牢抓住物体来移动物体。有些任务不能以这种方式完成,因为物体可能很脆弱,或者相对于机器人的手臂或手来说很大。例如,我们在移动一本合上的书时会用力握住,但在翻页时会用精致的手指动作。由于机器人的“手”可能相对于物体移动,因此机器人、物体和环境之间的接触类型在操纵过程中可能会发生变化。当接触条件不同时,施加在物体上的力会产生不同的运动。相反,不同的动议可能会导致未来不同的接触。规划计算方法可以确定可以完成任务的正确的力顺序和接触条件。在执行计划的动作期间出现的小错误通常可以通过采取纠正措施来减少。然而,这些纠正措施通常不会考虑到接触的变化,而且由于意外的接触,错误反而更加严重,最终导致任务失败。这个早期概念探索性研究资助(EAGER)项目将研究制定机器人运动计划的技术,以减轻而不是放大执行此类任务期间的错误。这种涉及重大接触事件的操作任务可以在机器人应用中找到,例如装载洗碗机、从杂乱的橱柜中取出难以够到的物体或移动家具。该项目团队将研究新的数据驱动方法来训练鲁棒的运动控制器,这些运动控制器源自贝叶斯神经网络,具有由机器人技术和控制原理提供的特殊结构。为了解决任务的接触丰富的性质,网络将由专家组成,其中每个专家要么是控制器,要么是用于派生基于被动性的控制器的存储函数。门控网络在给定网络输入的情况下选择使用哪个控制器。贝叶斯网络将在给定输入的情况下提供电机命令的分布,从而允许运动控制器考虑不确定性。该项目将分三个重叠阶段进行:研究人员将使用形式验证工具来合成可证明局部稳定接触丰富运动计划的控制器,并使用这些控制器使用知识蒸馏来初始化贝叶斯神经网络权重的先验分布。这个初始化的网络将使用来自可微模拟器的数据以端到端的方式从基于任务的奖励进行训练,其中机器人-物体-环境系统参数是不确定的。经过训练的网络将在实验中进行测试,其中包括机器人手臂推动一个大盒子越过阶梯状障碍物,这些障碍物设计需要在操作过程中改变接触条件。该项目如果成功,将确定一种控制器合成范例,同时克服模拟与现实之间的差距以及困扰纯数据驱动方法的接触丰富对象操作的数据效率低下问题。该项目还将推进扩大计算控制器合成方面的知识,并为随机系统的 GPU 加速模拟提供新工具。该奖项反映了 NSF 的法定使命,并通过使用基金会的智力优点和更广泛的影响审查进行评估,被认为值得支持标准。
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 }}
Hasan Poonawala其他文献
Invariant Set Estimation for Piecewise Affine Dynamical Systems Using Piecewise Affine Barrier Function
使用分段仿射势垒函数的分段仿射动力系统的不变集估计
- DOI:
10.48550/arxiv.2402.04243 - 发表时间:
2024-02-06 - 期刊:
- 影响因子:0
- 作者:
Pouya Samanipour;Hasan Poonawala - 通讯作者:
Hasan Poonawala
Hasan Poonawala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 }}
相似国自然基金
强壮前沟藻共生细菌降解膦酸酯产生促藻效应的分子机制
- 批准号:42306167
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
基于复合编码脉冲串的水下主动隐蔽性探测新方法研究
- 批准号:61271414
- 批准年份:2012
- 资助金额:60.0 万元
- 项目类别:面上项目
半定松弛与非凸二次约束二次规划研究
- 批准号:11271243
- 批准年份:2012
- 资助金额:60.0 万元
- 项目类别:面上项目
高效率强壮消息鉴别码的分析与设计
- 批准号:61202422
- 批准年份:2012
- 资助金额:23.0 万元
- 项目类别:青年科学基金项目
民航客运网络收益管理若干问题的研究
- 批准号:60776817
- 批准年份:2007
- 资助金额:20.0 万元
- 项目类别:联合基金项目
相似海外基金
CAREER: New data integration approaches for efficient and robust meta-estimation, model fusion and transfer learning
职业:新的数据集成方法,用于高效、稳健的元估计、模型融合和迁移学习
- 批准号:
2337943 - 财政年份:2024
- 资助金额:
$ 26.22万 - 项目类别:
Continuing Grant
CAREER: Robust Data Based Control and Estimation for Resilient DC Microgrids
职业:基于稳健数据的弹性直流微电网控制和估计
- 批准号:
2339434 - 财政年份:2024
- 资助金额:
$ 26.22万 - 项目类别:
Continuing Grant
DMS/NIGMS 1: Multilevel stochastic orthogonal subspace transformations for robust machine learning with applications to biomedical data and Alzheimer's disease subtyping
DMS/NIGMS 1:多级随机正交子空间变换,用于稳健的机器学习,应用于生物医学数据和阿尔茨海默病亚型分析
- 批准号:
2347698 - 财政年份:2024
- 资助金额:
$ 26.22万 - 项目类别:
Continuing Grant
SaTC: CORE: Small: Robust and Private Federated Analytics on Networked Data
SaTC:核心:小型:网络数据的稳健且私密的联合分析
- 批准号:
2241100 - 财政年份:2023
- 资助金额:
$ 26.22万 - 项目类别:
Standard Grant
Collaborative Research: IMR: MM-1A: Functional Data Analysis-aided Learning Methods for Robust Wireless Measurements
合作研究:IMR:MM-1A:用于稳健无线测量的功能数据分析辅助学习方法
- 批准号:
2319343 - 财政年份:2023
- 资助金额:
$ 26.22万 - 项目类别:
Continuing Grant