检索结果-内蒙古大学图书馆

Agnosticism gone awry: Why developmental robotics must commit to an understanding of embodiment and shared intentionality

引用

NEW IDEAS IN PSYCHOLOGY 2013年第3期31卷 184-193页

作者： Thompson, Joe J. Sameen, Nehdia Bibok, Maximilian B. Racine, Timothy P. Simon Fraser Univ Dept Psychol Burnaby BC V5A 1S6 Canada

We argue that developmental robotics, in its integration of developmental psychology and robotics, has the potential to encounter unexpected and unexamined conceptual difficulties. In particular, the various uses of embodiment and shared intentionality single out certain robots and behaviors as more or less relevant for the modeling of social cognition. As these terms have relatively orthogonal histories, there is no account for how their use will interact to shape methodology. We provide a brief discussion of how they may do so. Moreover, theorists often avoid explicit endorsement of some use or another. Although this agnosticism is understandable, we use the model of Dominey and Warneken (2011) as an illustrative example of why it is potentially dangerous. While Dominey and Warneken have succeeded in encouraging theorists to adopt clearer formulations of shared intentionality, their model suffers from important difficulties in interpretation, which, we argue, are a consequence of their uses of embodiment and shared intentionality respectively. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Shared intentionality Embodiment developmental robotics Situated cognition Synthetic modeling Social cognition

来源：评论

学校读者我要写书评

暂无评论

The role of intrinsic motivations in learning sensorimotor vocal mappings: a developmental robotics study

The role of intrinsic motivations in learning sensorimotor v...

引用

14th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2013)

作者： Moulin-Frier, Clement Oudeyer, Pierre-Yves INRIA FLOWERS Team Bordeaux France

ISBN: (纸本)9781629934433

Learning complex mappings between various modalities (typically articulatory, somatosensory and auditory) is a central issue in computationally modeling speech acquisition. These mappings are generally nonlinear and redundant, involving high dimensional sensorimotor spaces. Classical approaches consider two separate phases: a relatively pre-determined exploration phase analogous to infant babbling followed by an exploitation phase involving higher level communicative motivations. In this paper, we consider the problem as a developmental robotics one, in which an agent actively learns sensorimotor mappings of an articulatory vocal model. More specifically, we show how intrinsic motivations can allow the emergence of efficient exploration strategies, driving the way a learning agent will interact with its environment to collect an adequate learning set.

关键词： speech acquisition sensorimotor learning forward and inverse modeling developmental robotics intrinsic motivations active learning Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Why Are There developmental Stages in Language Learning? A developmental robotics Model of Language Development

引用

COGNITIVE SCIENCE 2017年第Suppl 1期41卷 32-51页

作者： Morse, Anthony F. Cangelosi, Angelo Univ Plymouth Ctr Robot & Neural Syst A311 Portland Sq Plymouth PL4 8AA Devon England

Most theories of learning would predict a gradual acquisition and refinement of skills as learning progresses, and while some highlight exponential growth, this fails to explain why natural cognitive development typically progresses in stages. Models that do span multiple developmental stages typically have parameters to "switch" between stages. We argue that by taking an embodied view, the interaction between learning mechanisms, the resulting behavior of the agent, and the opportunities for learning that the environment provides can account for the stage-wise development of cognitive abilities. We summarize work relevant to this hypothesis and suggest two simple mechanisms that account for some developmental transitions: neural readiness focuses on changes in the neural substrate resulting from ongoing learning, and perceptual readiness focuses on the perceptual requirements for learning new tasks. Previous work has demonstrated these mechanisms in replications of a wide variety of infant language experiments, spanning multiple developmental stages. Here we piece this work together as a single model of ongoing learning with no parameter changes at all. The model, an instance of the Epigenetic robotics Architecture (Morse et al 2010) embodied on the iCub humanoid robot, exhibits ongoing multi-stage development while learning pre-linguistic and then basic language skills.

关键词： developmental robotics Language learning Cognitive architecture Ongoing development

来源：评论

学校读者我要写书评

暂无评论

Modulation Based Transfer Learning of Motivational Cues in developmental robotics

Modulation Based Transfer Learning of Motivational Cues in D...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Romero, Alejandro Becerra, Jose A. Bellas, Francisco Duro, Richard J. Univ A Coruna Integrated Grp Engn Res La Coruna Spain

ISBN: (纸本)9781728119854

The modeling of utility is an important problem in many fields, including reinforcement learning. However, when considering a developmental approach to open-ended learning a new aspect arises. In these settings, the efficiency of the modeling process becomes a key aspect, as these processes usually take place in real time and, to increase survivability, it is necessary for the robot to be able to produce utility models as fast as possible. In this paper, we address this issue by proposing a modulation-based approach to the adaptation of the robot's experience, in the form of previously obtained ANN based utility models, to new situations. These previous utility models are perceptually recalled from a Long-Term Memory and combined to produce an initial guess to the new utility model. After this, modulatory structures are created that lead to the fine adaptation of these initial guesses to the real utility model of the new situation. Some initial results of experiments using a real robot are presented to clarify the approach. Specifically, three realistic problems that a Baxter "cooking robot" must solve are faced with this modulating approach. With them, it is clearly shown the increase in efficiency of the utility model learning in real time.

关键词： Motivational system Utility models Long-term memory Cognitive architecture developmental robotics

来源：评论

学校读者我要写书评

暂无评论

Self-Organizing Incremental Neural Network (SOINN) as a Mechanism for Motor Babbling and Sensory-Motor Learning in developmental robotics

Self-Organizing Incremental Neural Network (SOINN) as a Mech...

引用

12th International Work-Conference on Artificial Neural Networks (IWANN)

作者： Najjar, Tarek Hasegawa, Osamu Tokyo Inst Technol Dept Computat Intelligence & Syst Sci Midori Ku Yokohama Kanagawa 2268503 Japan

ISBN: (纸本)9783642386787

Learning how to control arm joints for goal-directed reaching tasks is one of the earliest skills that need to be acquired by developmental robotics in order to scaffold into tasks of higher Intelligence. Motor Babbling seems as a promising approach toward the generation of internal models and control policies for robotic arms. In this paper we propose a mechanism for learning sensory-motor associations using layered arrangement of Self-Organizing Neural Network (SOINN) and joint-egocentric representations. The robot starts off by random exploratory motion, then it gradually shift into more coordinated, goal-directed actions based on the measure of error-change. The main contribution of this research is in the proposition of a novel architecture for online sensory-motor learning using SOINN networks without the need to provide the system with a kinematic model or a preprogrammed joint control scheme. The viability of the proposed mechanism is demonstrated using a simulated planar robotic arm.

关键词： developmental robotics SOINN Self-organizing Neural Network Motor Babbling Sensory-Motor Learning Incremental Learning

来源：评论

学校读者我要写书评

暂无评论

Special issue on developmental robotics: Can experiments with machines inform theory in infant development?

引用

INFANT AND CHILD DEVELOPMENT 2008年第1期17卷 1-5页

作者： Prince, Christopher G. Univ Minnesota Dept Comp Sci Duluth MN 55812 USA

The article discusses various reports published within the issue including a study on developmental psychology and robotics and a paper on object perception and motor development.

关键词： developmental robotics modeling robotics Epigenetic robotics sensorimotor interaction embodiment theory

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimization for developmental robotics with Meta-Learning by Parameters Bounds Reduction 10

Bayesian Optimization for Developmental Robotics with Meta-L...

引用

10th Joint IEEE International Conference on Development and Learning and Epigenetic robotics (ICDL-EpiRob)

作者： Petit, Maxime Dellandrea, Emmanuel Chen, Liming Ecole Cent Lyon LIRIS CNRS UMR 5205 Ecully France

ISBN: (纸本)9781728173061

In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental framework based on long-term memory and reasoning modules (Bayesian Optimisation, visual similarity and parameters bounds reduction) allowing a robot to use meta-learning mechanism increasing the efficiency of such continuous and constrained parameters optimizations. The new optimization, viewed as a learning for the robot, can take advantage of past experiences (stored in the episodic and procedural memories) to shrink the search space by using reduced parameters bounds computed from the best optimizations realized by the robot with similar tasks of the new one (e.g. bin-picking from an homogenous heap of a similar object, based on visual similarity of objects stored in the semantic memory). As example, we have confronted the system to the constrained optimizations of 9 continuous hyper-parameters for a professional software (Kamido) in industrial robotic arm bin-picking tasks, a step that is needed each time to handle correctly new object. We used a simulator to create bin-picking tasks for 8 different objects (7 in simulation and one with real setup, without and with meta-learning with experiences coming from other similar objects) achieving goods results despite a very small optimization budget, with a better performance reached when meta-learning is used (84.3% vs 78.9% of success overall, with a small budget of 30 iterations for each optimization) for every object tested (p-value=0.036).

关键词： developmental robotics long-term memory meta learning hyperparmeters automatic optimization case-based reasoning

来源：评论

学校读者我要写书评

暂无评论

developmental robotics at Aldebaran A-Lab 13

Developmental robotics at Aldebaran A-Lab

引用

Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication

作者： Jean Christophe Baillie Aldebaran Robotics Aldebaran A-Lab Losserand Paris France

ISBN: (纸本)9781450320191

Aldebaran robotics is launching a developmental robotics activity as part of the new A-Lab research entity. The focus will be fundamental research and the scope of interest will range from low level categorization of sensorimotor information, up to high level lexical and grammatical language acquisition. I will shortly introduce the A-Lab and in particular the AI group with a rapid outlook on the research agenda and approach, stressing the potential for collaboration and the long term applicative view of the company.

关键词： language acquisition developmental robotics

来源：评论

学校读者我要写书评

暂无评论

Pointing Learning in developmental robotics Based on Constructive Neural Network and Reinforcement Learning Algorithm

Pointing Learning in Developmental Robotics Based on Constru...

引用

2011 IEEE International Conference on Intelligent Computing and Intelligent Systems(ICIS 2011)

作者： Fei Chao,Pan Wang,Minghui Shi,Min Jiang Cognitive Science Department Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University,Xiamen,Fujian,P.R.China,361005

This paper introduces a new approach to learning pointing behaviour in a developmental robot by using a type of constructive neural network and Q-learning algorithm,taking inspirations from human infant *** pointing behaviour is considered as the first movement that human infants use to communicate with other person during human development,it is also the foundation of the human social interaction *** rebuilt this developmental course in our robot simulation *** learning algorithm of the pointing is implemented by Q-Learning,and a radial based function neural network with resource allocating algorithm is applied to hold the learning result and to control robot *** experimental results show that the approach is able to lead our development robot to generate pointing behaviour.

关键词： Index Terms-Pointing Learning developmental robotics Constructive Neural Network

来源：评论

学校读者我要写书评

暂无评论

Embodied Attention in Word-Object Mapping: A developmental Cognitive robotics Model

Embodied Attention in Word-Object Mapping: A Developmental C...

引用

IEEE International Conference on Development and Learning (ICDL)

作者： Raggioli, Luca Cangelosi, Angelo Univ Manchester Dept Comp Sci Manchester Lancs England

ISBN: (数字)9781665413114

ISBN: (纸本)9781665413114

developmental robotics models provide useful tools to study and understand the language learning process in infants and robots. These models allow us to describe key mechanisms of language development, such as statistical learning, the role of embodiment, and the impact of the attention payed to an object while learning its name. Robots can be particularly well suited for this type of problems, because they cover both a physical manipulation of the environment and mathematical modeling of the temporal changes of the learned concepts. In this work we present a computational representation of the impact of embodiment and attention on word learning, relying on sensory data collected with a real robotic agent in a real world scenario. Results show that the cognitive architecture designed for this scenario is able to capture the changes underlying the moving object in the field of view of the robot. The architecture successfully handles the temporal relationship in moving items and manages to show the effects of the embodied attention on word-object mapping.

关键词： developmental robotics cognitive architectures word-object mapping language learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：