S&AS: FND: Reflective Learning of Stochastic Physical Models for Robust Manipulation

S

• 批准号: 1723869
• 负责人: Abdeslam Boularias
• 金额: $ 68.26万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1723869&HistoricalAwards=false
• 关键词: S& FND; Reflective; Learning; Stochastic

In order for robots to function in everyday life environments, from flexible manufacturing and warehouse domains to households, they need to autonomously grasp and manipulate a wide variety of potentially unknown objects. Currently, autonomous robots are practically unable to work outside highly-controlled environments wherein an accurate model of every object is provided. This limitation is partially due to the lack of robust algorithms for grasping and manipulating objects with unknown geometric or mechanical properties. The proposed project will perform fundamental research into robust robotic manipulation in a way that will enable autonomous robots to interact efficiently with a large variety of everyday physical objects for extended periods of time. The objective is for autonomous robotic manipulators to effectively learn from experience how objects may physically interact with each other and with the robotic arm. The next step is to utilize this experience so as to perform robust manipulation tasks. There are many exemplary robotic tasks that can be benefited from the proposed improvements and which will form the basis of the project's experimentation process. They include the pushing of objects to desired poses, reconfiguration of objects to simplify their picking and the handling of tools. The project develops three key components: (1) An algorithm for learning inertial, elastic, and friction properties of an unknown object by observing how the object moves when manipulated by a robot. The project will research novel Bayesian optimization techniques for black-box system identification in order to learn probabilistic models of objects. (2) A physically realistic simulator that can provide a stochastic model of an object's motion given the physical parameters learned by the first component. This will be achieved by utilizing online non-parametric learning methods for speeding up physically realistic simulations under uncertainty. (3), A robust planning algorithm that utilizes the simulator for finding optimal actions to apply on the object given the learned stochastic model. The objective is to converge to increasingly robust solutions as computation time increases and the robot acquires increased experience with objects in an environment. To strengthen the project's broader impact, the PIs will provide implementations of their solutions to the research community as open-source software packages. This will be coupled with the generation of educational material, which will aim to attract undergraduate students early in their studies to STEM. The PIs will also aim to organize academic meetings that will bring together researchers from foundational domains, robotics experts and industry representatives.

为了让机器人在日常生活环境中发挥作用，从灵活的制造和仓库领域到家庭，它们需要自主地抓取和操纵各种潜在的未知物体。目前，自主机器人实际上无法在高度受控的环境下工作，在这种环境中，每个对象都提供了准确的模型。这一限制部分是由于缺乏用于抓取和操纵具有未知几何或机械属性的对象的健壮算法。拟议的项目将对健壮的机器人操作进行基础研究，使自主机器人能够在更长的时间内与各种日常物理物体有效互动。其目标是让自主机器人操作员有效地从经验中学习物体如何相互作用以及如何与机械臂进行物理交互。下一步是利用这一经验来执行健壮的操作任务。有许多示范性的机器人任务可以从拟议的改进中受益，这些任务将构成该项目实验过程的基础。它们包括将对象推到所需的姿势，重新配置对象以简化其拾取和工具的操作。该项目开发了三个关键组件：(1)一种通过观察机器人操作时对象的运动方式来学习未知对象的惯性、弹性和摩擦属性的算法。该项目将研究新的贝叶斯优化技术用于黑匣子系统识别，以学习对象的概率模型。(2)物理上逼真的模拟器，它可以在给定第一个组件学习到的物理参数的情况下提供对象运动的随机模型。这将通过利用在线非参数学习方法来加速不确定情况下的物理真实模拟来实现。(3)，一种稳健的规划算法，它利用模拟器在给定学习的随机模型的情况下找到应用于对象的最优动作。目标是随着计算时间的增加和机器人获得与环境中对象的更多体验而收敛到越来越健壮的解。为了加强该项目的更广泛影响，私人投资机构将以开放源码软件包的形式向研究界提供其解决方案的实施。此外，还将编写教材，旨在吸引刚开始学习的本科生进入STEM学习。PIS还将致力于组织学术会议，将来自基础领域的研究人员、机器人专家和行业代表聚集在一起。

项目成果

Anytime motion planning for prehensile manipulation in dense clutter

随时进行运动规划，以便在密集的杂乱环境中进行抓握操作

• DOI: 10.1080/01691864.2019.1690207
• 发表时间: 2019
• 期刊: Advanced Robotics
• 影响因子: 2
• 作者: Kimmel, Andrew;Shome, Rahul;Bekris, Kostas
• 通讯作者: Bekris, Kostas

Learning to Slide Unknown Objects with Differentiable Physics Simulations

学习通过可微分物理模拟滑动未知物体

• DOI: 10.15607/rss.2020.xvi.099
• 发表时间: 2020
• 期刊: Robotics science and systems
• 作者: Song, Changkyu;Boularias, Abdeslam
• 通讯作者: Boularias, Abdeslam

Safe and Effective Picking Paths in Clutter given Discrete Distributions of Object Poses

给定物体姿态离散分布的杂波中安全有效的拾取路径

• 发表时间: 2020
• 期刊: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS
• 作者: Wang, R;Mitash, C;Boehm, D;Bekris, K E
• 通讯作者: Bekris, K E

Physics-based scene-level reasoning for object pose estimation in clutter

• DOI: 10.1177/0278364919846551
• 发表时间: 2022-05-01
• 期刊: INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
• 影响因子: 9.2
• 作者: Mitash, Chaitanya;Boularias, Abdeslam;Bekris, Kostas
• 通讯作者: Bekris, Kostas

The interaction between map complexity and crowd movement on navigation decisions in virtual reality

虚拟现实中地图复杂性和人群运动对导航决策的相互作用

• DOI: 10.1098/rsos.191523
• 发表时间: 2020
• 期刊: Royal Society Open Science
• 影响因子: 3.5
• 作者: Zhao, Hantao;Thrash, Tyler;Grossrieder, Armin;Kapadia, Mubbasir;Moussaïd, Mehdi;Hölscher, Christoph;Schinazi, Victor R.
• 通讯作者: Schinazi, Victor R.