Abstract Concept Learning in Cognitive Robots

Abstract Concept Learning in Cognitive Robots
复制标题

认知机器人中的抽象概念学习

DOI:
10.1007/s43154-020-00038-x
复制
发表时间:
2021
期刊:
Current Robotics Reports
影响因子:
--
通讯作者:
Di Nuovo A
Di Nuovo A
中科院分区:
--
文献类型:
--
作者:
Di Nuovo A

文献摘要

参考文献

相似文献

理解和操纵抽象概念是人类智能的一个基本特征,目前在人工智能中缺失。没有它,这些机器人在执行任务时与人类进行社交互动的能力将受到阻碍。然而,我们需要什么来赋予我们的机器人这样的能力?在这篇文章中,我们讨论了最近的一些尝试认知机器人建模这些概念的基础上,一些neurophysiological principles.Recent FindingsFor高级学习的抽象概念,人工代理需要一个(机器人)的身体,因为抽象和具体的概念被认为是一个连续体,抽象的概念可以通过将它们连接到具体的体现感知来学习。开创性的研究提供了有价值的信息模拟人工学习,并证明了价值的认知机器人方法来研究方面的abstract cognition.SummaryThere是一些成功的例子,认知模型的抽象知识的基础上连接主义和概率建模技术。然而,机器人抽象概念学习的建模目前仅限于窄任务。为了取得进一步的进展,我们认为,需要多个学科之间更密切的合作,以分享专业知识和共同设计未来的研究。特别重要的是创建和共享人类学习行为的基准数据集。
Purpose of ReviewUnderstanding and manipulating abstract concepts is a fundamental characteristic of human intelligence that is currently missing in artificial agents. Without it, the ability of these robots to interact socially with humans while performing their tasks would be hindered. However, what is needed to empower our robots with such a capability? In this article, we discuss some recent attempts on cognitive robot modeling of these concepts underpinned by some neurophysiological principles.Recent FindingsFor advanced learning of abstract concepts, an artificial agent needs a (robotic) body, because abstract and concrete concepts are considered a continuum, and abstract concepts can be learned by linking them to concrete embodied perceptions. Pioneering studies provided valuable information about the simulation of artificial learning and demonstrated the value of the cognitive robotics approach to study aspects of abstract cognition.SummaryThere are a few successful examples of cognitive models of abstract knowledge based on connectionist and probabilistic modeling techniques. However, the modeling of abstract concept learning in robots is currently limited at narrow tasks. To make further progress, we argue that closer collaboration among multiple disciplines is required to share expertise and co-design future studies. Particularly important is to create and share benchmark datasets of human learning behavior.
智能机器人需要情感吗?
DOI: 10.1016/j.tics.2017.06.010
发表时间: 2017
影响因子: 19.9
作者:
Pessoa,Luiz
通讯作者: Pessoa,Luiz
DOI: 10.1109/ijcnn.2018.8489140
发表时间: 2018
期刊: 2018 International Joint Conference on Neural Networks (IJCNN)
影响因子: --
作者:
A. D. Nuovo
通讯作者: A. D. Nuovo
DOI: 10.1016/j.cortex.2007.08.001
发表时间: 2008-04-01
期刊: CORTEX
影响因子: 3.6
作者:
Domahs, Frank;Krinzinger, Helga;Willmes, Klaus
通讯作者: Willmes, Klaus
机器人时代系统的接受度:机器人在智能环境中为老年人提供服务的结果
DOI: 10.2196/preprints.9460
发表时间: 2018
影响因子: 3
作者:
F. Cavallo;R. Bevilacqua
通讯作者: R. Bevilacqua
DOI: 10.3758/s13423-014-0696-0
发表时间: 2015-04-01
影响因子: 3.5
作者:
Moffat, Michael;Siakaluk, Paul D.;Pexman, Penny M.
通讯作者: Pexman, Penny M.