Learning the Context in Programming by Demonstration of Manipulation Tasks

通过演示操作任务来学习编程环境

基本信息

项目摘要

State-of-the-art service robots are able to learn new manipulation tasks consisting of multiple, defined actions, based on the observation of a human teacher, known as Programming by Demonstration (PbD). The logic structure of the task characterized by branches or alternative actions, can be learned using symbolic PbD-approaches. Subsymbolic PbD-approaches allow to learn atomic actions, which generate executable robot motions.. However, no information about the context, in which the atomic action can be executed, is generated. In order to execute a manipulation task autonomously, an operational description of the context is necessary. The problem to solve is, what are relevant, measurable object properties and how can they be autonomously observed with high reliability by the robot.Visual perception alone is insufficient since the variety of objects in the human environment leads to a large number of ambiguities and false positives. The basis to resolve these issues is a selection of suitable object classifiers, a reduced number of objects to classify and the definition of search regions. Additionally, sensor actions have to be defined to determine object properties, which can't be measured visually. In most state-of-the-art systems, this knowledge is defined manually.Thus, the goal of this project is to extend the PbD-approach to learn the context of a manipulation task based on human observation. In order to achieve this goal, we will integrate and extend methods from scene analysis into the PbD-approach. The second goal is to resolve ambiguities and detect false positives of visual perception algorithms using the learned contexts. We will integrate and extend methods from interactive object detection into the PbD-approach to learn sensor actions efficiently to measure non-visual object properties, e.g. weight, and thereby resolve ambiguities and false detections. Based on the learned context, we can infer the role of unknown objects in the environment, e.g. based on the spatial relation to known objects. The execution of learned manipulation tasks with an object, which was unknown , is without generalization processes not possible. Thus, increasing the generalization capabilities of the robot by interactively adapting learned constraints and goals of a manipulation task to a novel object. The application of morphing methods is planned to transform constraints and goals on the basis of 3D-object-models. With the help of simulation techniques the verification of the transformation and its adjustment is done interactively. The developed algorithms will be implemented on real robot anthropomorphic systems and evaluated using real world examples.
最先进的服务机器人能够根据人类老师的观察,学习由多个定义动作组成的新操作任务,称为编程演示(PbD)。任务的逻辑结构以分支或替代动作为特征,可以使用符号pbd方法来学习。亚符号pbd方法允许学习原子动作,从而生成可执行的机器人动作。但是,不会生成有关可以执行原子操作的上下文的信息。为了自主地执行操作任务,上下文的操作描述是必要的。要解决的问题是,什么是相关的、可测量的物体属性,以及如何让机器人以高可靠性自主地观察它们。仅凭视觉感知是不够的,因为人类环境中物体的多样性会导致大量的歧义和误报。解决这些问题的基础是选择合适的对象分类器、减少要分类的对象数量和定义搜索区域。此外,必须定义传感器动作以确定物体属性,这是无法通过视觉测量的。在大多数最先进的系统中,这些知识是手动定义的。因此,本项目的目标是扩展pbd方法,以学习基于人类观察的操作任务的上下文。为了实现这一目标,我们将把场景分析方法整合和扩展到pbd方法中。第二个目标是利用学习到的上下文来解决歧义和检测视觉感知算法的误报。我们将集成并扩展交互式对象检测方法到pbd方法中,以有效地学习传感器动作来测量非视觉对象属性,例如重量,从而解决歧义和错误检测。基于学习到的上下文,我们可以推断未知物体在环境中的作用,例如,基于与已知物体的空间关系。如果没有泛化过程,对未知对象执行习得的操作任务是不可能的。因此,通过交互式地适应学习到的约束和操作任务的目标来提高机器人的泛化能力。在三维对象模型的基础上,计划应用变形方法对约束和目标进行转换。在仿真技术的帮助下,进行了转换和调整的交互式验证。开发的算法将在真实的机器人拟人化系统上实施,并使用真实世界的示例进行评估。

项目成果

期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Scene recognition for mobile robots by relational object search using Next-Best-View estimates from hierarchical Implicit Shape Models
使用分层隐式形状模型的下一个最佳视图估计,通过关系对象搜索来进行移动机器人的场景识别
Active scene recognition for programming by demonstration using next-best-view estimates from hierarchical Implicit Shape Models
通过使用分层隐式形状模型中的次最佳视图估计进行演示,进行主动场景识别以进行编程
Automated selection of spatial object relations for modeling and recognizing indoor scenes with hierarchical Implicit Shape Models
自动选择空间对象关系,用于使用分层隐式形状模型建模和识别室内场景
{{ 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 }}

Professor Dr.-Ing. Rüdiger Dillmann其他文献

Professor Dr.-Ing. Rüdiger Dillmann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('Professor Dr.-Ing. Rüdiger Dillmann', 18)}}的其他基金

Situationsinterpretation und Verhaltensplanung unter Unsicherheiten für kognitive Automobile
认知汽车不确定性下的态势解释与行为规划
  • 批准号:
    194098769
  • 财政年份:
    2011
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Situationsbezogene Erweiterte Realität im Operationssaal
手术室情景增强现实
  • 批准号:
    59266434
  • 财政年份:
    2008
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Patientenspezifische Simulation der aortalen Blutströmung unter Berücksichtigung der Gefäßwandinteraktion
考虑血管壁相互作用的针对患者的主动脉血流模拟
  • 批准号:
    42635322
  • 财政年份:
    2007
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Visuelle Sensorplattform für kognitive Automobile
用于认知汽车的视觉传感器平台
  • 批准号:
    5417621
  • 财政年份:
    2003
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Computergestützte Planung und Navigation neurochirurgischer Eingriffe an der Wirbelsäule
脊柱神经外科手术的计算机辅助规划和导航
  • 批准号:
    5390712
  • 财政年份:
    2002
  • 资助金额:
    --
  • 项目类别:
    Priority Programmes
Schritthaltendes Lernen dreidimensionaler geometrischer Umweltkarten durch Autonome Inspektionsfahrzeuge
自动检测车对三维几何环境图的同步学习
  • 批准号:
    5342756
  • 财政年份:
    2002
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Rechnerarchitektur, Sensorik und adaptive Steuerung einer vierbeinigen Laufmaschine mit dynamisch stabilem Gang
动态稳定步态四足行走机的计算机体系结构、传感器和自适应控制
  • 批准号:
    5383003
  • 财政年份:
    1997
  • 资助金额:
    --
  • 项目类别:
    Priority Programmes
Programmieren durch Vormachen unter Verwendung eines aktiven Stereo-Sichtsystems und eines Datenhandschuhs
使用主动立体视觉系统和数据手套进行演示编程
  • 批准号:
    5252037
  • 财政年份:
    1996
  • 资助金额:
    --
  • 项目类别:
    Research Grants

相似国自然基金

基于Context建模的基因组数据压缩研究
  • 批准号:
    61861045
  • 批准年份:
    2018
  • 资助金额:
    35.0 万元
  • 项目类别:
    地区科学基金项目
Focus+Context支持的群集三维对象变形可视化
  • 批准号:
    41671381
  • 批准年份:
    2016
  • 资助金额:
    65.0 万元
  • 项目类别:
    面上项目
基于Context建模的熵编码及其应用研究
  • 批准号:
    61062005
  • 批准年份:
    2010
  • 资助金额:
    22.0 万元
  • 项目类别:
    地区科学基金项目

相似海外基金

Role of PARP-mediated NAD+ depletion in the establishment of Placental Dysfunction and Fetal Programming in the context of Maternal Obesity
PARP 介导的 NAD 耗竭在孕产妇肥胖背景下胎盘功能障碍和胎儿编程中的作用
  • 批准号:
    486237
  • 财政年份:
    2022
  • 资助金额:
    --
  • 项目类别:
    Studentship Programs
Early Life Adversity and the Developmental Programming of Early Childhood Telomere Biology: A Longitudinal Study of Developmental Context and Behavioral Mediators
早期生活逆境与幼儿期端粒生物学的发展规划:发展背景和行为中介的纵向研究
  • 批准号:
    10297293
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
Early Life Adversity and the Developmental Programming of Early Childhood Telomere Biology: A Longitudinal Study of Developmental Context and Behavioral Mediators
早期生活逆境与幼儿期端粒生物学的发展规划:发展背景和行为中介的纵向研究
  • 批准号:
    10649546
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
Programming as a Context for Making Problem Solving Visible: An Equity Focused K-5 Research Practice Partnership
编程作为使问题解决变得可见的背景:以公平为中心的 K-5 研究实践合作伙伴关系
  • 批准号:
    1837488
  • 财政年份:
    2019
  • 资助金额:
    --
  • 项目类别:
    Standard Grant
Placental programming of infant neurodevelopment in the context of maternal care
孕产妇护理背景下婴儿神经发育的胎盘编程
  • 批准号:
    1942116
  • 财政年份:
    2017
  • 资助金额:
    --
  • 项目类别:
    Studentship
Context-Oriented Programming Framework and Methodology for Robot Operating System
机器人操作系统面向上下文的编程框架和方法
  • 批准号:
    17K00079
  • 财政年份:
    2017
  • 资助金额:
    --
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
High-level programming paradigm for context-aware computing
上下文感知计算的高级编程范例
  • 批准号:
    121667-2007
  • 财政年份:
    2014
  • 资助金额:
    --
  • 项目类别:
    Discovery Grants Program - Individual
High-level programming paradigm for context-aware computing
上下文感知计算的高级编程范例
  • 批准号:
    121667-2007
  • 财政年份:
    2013
  • 资助金额:
    --
  • 项目类别:
    Discovery Grants Program - Individual
High-level programming paradigm for context-aware computing
上下文感知计算的高级编程范例
  • 批准号:
    121667-2007
  • 财政年份:
    2012
  • 资助金额:
    --
  • 项目类别:
    Discovery Grants Program - Individual
High-level programming paradigm for context-aware computing
上下文感知计算的高级编程范例
  • 批准号:
    121667-2007
  • 财政年份:
    2011
  • 资助金额:
    --
  • 项目类别:
    Discovery Grants Program - Individual
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了