RoboSherlock - Scaling Robot Perception towards Everyday Manipulation through Unstructured Information Processing
RoboSherlock - 通过非结构化信息处理将机器人感知扩展到日常操作
基本信息
- 批准号:260410154
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:德国
- 项目类别:Research Grants
- 财政年份:2015
- 资助国家:德国
- 起止时间:2014-12-31 至 2017-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
We propose the design, implementation, and empirical analysis of RoboSherlock, a novel robot perception framework for facilitating everyday manipulation activities with objects of daily use in human living environments. The aim of the RoboSherlock project is to equip robots with perception systems that are flexible, accurate, and robust without having to interrupt ongoing activity. This is achieved by equipping the perception system with the following capabilities:- lifelong learning and adaptation for everyday activity,- powerful first-order probabilistic reasoning,- knowledge- and model-based perception methods, and- proactive and anticipatory perception.In order to implement RoboSherlock we consider perception as an unstructured information processing and management problem. Unstructured information management (UIM) has proven itself to be a powerful paradigm for scaling intelligent information and question answering systems towards real-world complexity. Complexity in UIM is handled by identifying (or hypothesizing) pieces of structured information in unstructured documents, by applying ensembles of experts for annotating information pieces, and by testing and integrating these isolated annotations into a comprehensive interpretation of the document. In the RoboSherlock project we will transfer these methods to robot perception in order to scale it to realistic perception tasks in realistic environments.The perception capabilities implemented in RoboSherlock will be evaluated and empirically analyzed in the context of a robotic agent that performs fetch and place tasks for everyday activities, 5 days a week for several weeks, such as setting the table, cleaning up, loading and unloading the dishwasher, etc.
我们提出了RoboSherlock的设计,实现和实证分析,RoboSherlock是一种新型的机器人感知框架,用于在人类生活环境中使用日常使用的对象进行日常操作活动。RoboSherlock项目的目标是为机器人配备灵活、准确和强大的感知系统,而不必中断正在进行的活动。 这是通过为感知系统配备以下功能来实现的:-终身学习和适应日常活动,-强大的一阶概率推理,-基于知识和模型的感知方法,以及-主动和预期的感知。为了实现RoboSherlock,我们将感知视为非结构化的信息处理和管理问题。 非结构化信息管理(UIM)已被证明是一个强大的范例,用于将智能信息和问答系统扩展到现实世界的复杂性。UIM中的复杂性是通过识别(或假设)非结构化文档中的结构化信息片段,通过应用专家集合来注释信息片段,以及通过测试和将这些孤立的注释集成到文档的综合解释中来处理的。在RoboSherlock项目中,我们将把这些方法转移到机器人感知中,以便将其扩展到现实环境中的现实感知任务。RoboSherlock中实现的感知能力将在机器人代理的背景下进行评估和经验分析,该机器人代理执行日常活动的获取和放置任务,每周5天,持续数周,例如布置桌子、清理、装载和卸载洗碗机等。
项目成果
期刊论文数量(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Storing and retrieving perceptual episodic memories for long-term manipulation tasks
- DOI:10.1109/icar.2017.8023492
- 发表时间:2017-07
- 期刊:
- 影响因子:0
- 作者:Ferenc Bálint-Benczédi;Zoltán-Csaba Márton;M. Durner;M. Beetz
- 通讯作者:Ferenc Bálint-Benczédi;Zoltán-Csaba Márton;M. Durner;M. Beetz
{{
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. Michael Beetz, Ph.D.其他文献
Professor Dr. Michael Beetz, Ph.D.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. Michael Beetz, Ph.D.', 18)}}的其他基金
PIPE: Probabilistic Models of Instructions, Perception andExperience - Representation, Learning and Reasoning
PIPE:指令、感知和经验的概率模型 - 表示、学习和推理
- 批准号:
322037152 - 财政年份:2017
- 资助金额:
-- - 项目类别:
Research Grants
Autonomous Learning for Bayesian Cognitive Robotics
贝叶斯认知机器人的自主学习
- 批准号:
200306665 - 财政年份:2011
- 资助金额:
-- - 项目类别:
Priority Programmes
Automated Sport Game Analysis Model (ASPOGAMO) - ein automatisiertes, umfassendes Modell zur Analyse von Sportspielen
自动体育比赛分析模型 (ASPOGAMO) - 用于分析体育比赛的自动化综合模型
- 批准号:
51462600 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Research Grants
ActAR - Aktionsbewusstsein für kognitive Roboter
ActAR - 认知机器人的动作意识
- 批准号:
38295211 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Research Grants
MeMoMan2 - Methods for real-time accurate Model-based Measurement of HuMan Motion
MeMoMan2 - 基于模型的实时精确人体运动测量方法
- 批准号:
14188462 - 财政年份:2005
- 资助金额:
-- - 项目类别:
Research Grants
Interaktive, plan-basierte Softwareagenten im verteilten Supply Chain Management
分布式供应链管理中基于计划的交互式软件代理
- 批准号:
5246994 - 财政年份:2000
- 资助金额:
-- - 项目类别:
Priority Programmes
Modell- und diagnosebasiertes Transformationslernen von symbolischen Kontrollprogrammen für mobile Roboter
基于模型和诊断的移动机器人符号控制程序的转换学习
- 批准号:
5214552 - 财政年份:2000
- 资助金额:
-- - 项目类别:
Research Grants
Lifespan AI - Project M2: Lifespan Knowledge Representation
寿命AI - 项目M2:寿命知识表示
- 批准号:
498597191 - 财政年份:
- 资助金额:
-- - 项目类别:
Research Units
Artificial Intelligence for Human-Robot Interaction
人机交互人工智能
- 批准号:
442588247 - 财政年份:
- 资助金额:
-- - 项目类别:
Research Grants
相似海外基金
Scaling-Up plant based Nanocarriers for BIOpharmaceuticals (SUNBIO)
用于生物制药的植物纳米载体的放大(SUNBIO)
- 批准号:
EP/Z53304X/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
Scaling-up co-designed adolescent mental health interventions
扩大共同设计的青少年心理健康干预措施
- 批准号:
MR/Y020286/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Fellowship
Stochastic processes in random environments with inhomogeneous scaling limits
具有不均匀缩放限制的随机环境中的随机过程
- 批准号:
24K06758 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (C)
The challenge of scaling methane fluxes in mangrove and mountain forests for an accurate methane budget
缩放红树林和山地森林甲烷通量以获得准确的甲烷预算的挑战
- 批准号:
24K01797 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (B)
HSI Implementation and Evaluation Project: Scaling and Extending Exploratory Reading Groups to Strengthen Computing Pathways
HSI 实施和评估项目:扩大和扩展探索性阅读小组以加强计算途径
- 批准号:
2414332 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Continuing Grant
Place-based approaches to sustainable food supply chains: scaling socio-technical innovations as enablers for enhancing public sector food procurement
基于地方的可持续食品供应链方法:扩大社会技术创新作为加强公共部门食品采购的推动力
- 批准号:
ES/Z502807/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
Beyond experiments: scaling transformative, sustainable business models in the UK
超越实验:在英国扩展变革性、可持续的商业模式
- 批准号:
MR/X035786/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Fellowship
Study on mitigation of gypsum scaling during membrane distillation operation
膜蒸馏运行过程中石膏结垢缓解研究
- 批准号:
24K17543 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Early-Career Scientists
Oxygen vacancy engineering on indium oxide vertical FETs for 3D power scaling
用于 3D 功率缩放的氧化铟垂直 FET 上的氧空位工程
- 批准号:
24K17328 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Early-Career Scientists