检索结果-内蒙古大学图书馆

GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning

IEEE TRANSACTIONS ON COGNITIVE AND developmental SYSTEMS 2016年第3期8卷 214-231页

作者： Santucci, Vieri Giuliano Baldassarre, Gianluca Mirolli, Marco Consiglio Nazl Ricerce Ist Sci & Tecnol Cogniz I-00185 Rome Italy Univ Plymouth Sch Comp & Math Plymouth PL4 8AA Devon England

In this paper, we present goal-discovering robotic architecture for intrisically-motivated learning (GRAIL), a four-level architecture that is able to autonomously: 1) discover changes in the environment;2) form representations of the goals corresponding to those changes;3) select the goal to pursue on the basis of intrinsic motivations (IMs);4) select suitable computational resources to achieve the selected goal;5) monitor the achievement of the selected goal;and 6) self-generate a learning signal when the selected goal is successfully achieved. Building on previous research, GRAIL exploits the power of goals and competence-based IMs to autonomously explore the world and learn different skills that allow the robot to modify the environment. To highlight the features of GRAIL, we implement it in a simulated iCub robot and test the system in four different experimental scenarios where the agent has to perform reaching tasks within a 3-D environment.

关键词： Autonomous robotics developmental robotics goal formation hierarchical architecture intrinsic motivations (IMs) reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Developing navigation behavior through self-organizing distinctive-state abstraction

引用

CONNECTION SCIENCE 2006年第2期18卷 159-172页

作者： Provost, Jefferson Kuipers, Benjamin J. Mlikkulainen, Risto Univ Texas Artificial Intelligence Lab Neural Networks Res Grp Austin TX 78712 USA Univ Texas Intelligent Robot Lab Austin TX 78712 USA

A major challenge in reinforcement learning research is to extend the methods that have worked well on discrete, short-range, low-dimensional problems to continuous, high-diameter, high-dimensional problems, such as robot navigation using high-resolution sensors. Self-organizing distinctive-state abstraction (SODA) is a new, generic method by which a robot in a continuous world can better learn to navigate, by learning a set of high-level features and building temporally extended actions to carry it between distinctive states based on those features. A SODA agent first uses a self-organizing feature map to develop a set of high-level perceptual features while exploring the environment with primitive, local actions. The agent then builds a set of high-level actions composed of generic trajectory-following and hill-climbing control laws that carry it between the states at local maxima of feature activations. In an experiment on a simulated robot navigation task, the SODA agent learns to perform a task requiring 300 small-scale, local actions using as few as nine new, temporally extended actions, significantly improving learning time over navigating with the local actions.

关键词： developmental robotics self-organization reinforcement learning robot navigation

来源：评论

学校读者我要写书评

暂无评论

Explaining Aha! moments in artificial agents through IKE-XAI: Implicit Knowledge Extraction for eXplainable AI

引用

NEURAL NETWORKS 2022年 155卷 95-118页

作者： Kaadoud, Ikram Chraibi Bennetot, Adrien Mawhin, Barbara Charisi, Vicky Diaz-Rodriguez, Natalia IMT Atlantique Lab STICC UMR CNRS 6285 F-29238 Brest France Inst Polytech Paris Inria Flowers Team ENSTA U2IS Dept 828 Blvd Marechaux F-91762 Palaiseau France Segula Technol Parc Activite Pissaloup Trappes France Sorbonne Univ Inst Syst Intelligents & Robot Paris France EBT Salient Aero Fdn Human Factors Dept Seville Spain European Commiss Joint Res Ctr JRC Seville Spain Univ Granada Dept Comp Sci & Artificial Intelligence DaSCI Andalusian Inst Data Sci & Computat Intelli E-18071 Granada Spain

During the learning process, a child develops a mental representation of the task he or she is learning. A Machine Learning algorithm develops also a latent representation of the task it learns. We investigate the development of the knowledge construction of an artificial agent through the analysis of its behavior, i.e., its sequences of moves while learning to perform the Tower of Hanoi (TOH) task. The TOH is a well-known task in experimental contexts to study the problem-solving processes and one of the fundamental processes of children's knowledge construction about their world. We position ourselves in the field of explainable reinforcement learning for developmental robotics, at the crossroads of cognitive modeling and explainable AI. Our main contribution proposes a 3-step methodology named Implicit Knowledge Extraction with eXplainable Artificial Intelligence (IKE-XAI) to extract the implicit knowledge, in form of an automaton, encoded by an artificial agent during its learning. We showcase this technique to solve and explain the TOH task when researchers have only access to moves that represent observational behavior as in human-machine interaction. Therefore, to extract the agent acquired knowledge at different stages of its training, our approach combines: first, a Q-learning agent that learns to perform the TOH task;second, a trained recurrent neural network that encodes an implicit representation of the TOH task;and third, an XAI process using a post-hoc implicit rule extraction algorithm to extract finite state automata. We propose using graph representations as visual and explicit explanations of the behavior of the Q-learning agent. Our experiments show that the IKE-XAI approach helps understanding the development of the Q-learning agent behavior by providing a global explanation of its knowledge evolution during learning. IKE-XAI also allows researchers to identify the agent's Aha! moment by determining from what moment the knowledge representation s

关键词： Explainable AI Reinforcement learning Cognitive modeling developmental robotics Post-hoc rule extraction Knowledge extraction

来源：评论

学校读者我要写书评

暂无评论

Integrating visual perception and manipulation for autonomous learning of object representations

引用

ADAPTIVE BEHAVIOR 2013年第5期21卷 328-345页

作者： Schiebener, David Morimoto, Jun Asfour, Tamim Ude, Ales Jozef Stefan Inst Ljubljana Slovenia Karlsruhe Inst Technol D-76021 Karlsruhe Germany ATR Computat Neurosci Labs Dept Brain Robot Interface Kyoto Japan Karlsruhe Inst Technol Inst Anthropomat D-76021 Karlsruhe Germany Jozef Stefan Inst Dept Automat Biocybernet & Robot Humanoid & Cognit Robot Lab Ljubljana Slovenia ATR Computat Neurosci Labs Kyoto Japan

Humans can effortlessly perceive an object they encounter for the first time in a possibly cluttered scene and memorize its appearance for later recognition. Such performance is still difficult to achieve with artificial vision systems because it is not clear how to define the concept of objectness in its full generality. In this paper we propose a paradigm that integrates the robot's manipulation and sensing capabilities to detect a new, previously unknown object and learn its visual appearance. By making use of the robot's manipulation capabilities and force sensing, we introduce additional information that can be utilized to reliably separate unknown objects from the background. Once an object has been identified, the robot can continuously manipulate it to accumulate more information about it and learn its complete visual appearance. We demonstrate the feasibility of the proposed approach by applying it to the problem of autonomous learning of visual representations for viewpoint-independent object recognition on a humanoid robot.

关键词： Humanoid robotics developmental robotics object perception active vision

来源：评论

学校读者我要写书评

暂无评论

Attribution of autonomy and its role in robotic language acquisition

引用

AI & SOCIETY 2022年第2期37卷 605-617页

作者： Forster, Frank Althoefer, Kaspar Queen Mary Univ London Ctr Adv Robot Queen Mary ARQ Mile End Rd London E1 4NS England Univ Hertfordshire Sch Phys Engn & Comp Sci Adapt Syst Res Grp Coll Lane Hatfield AL10 9AB Herts England

The false attribution of autonomy and related concepts to artificial agents that lack the attributed levels of the respective characteristic is problematic in many ways. In this article, we contrast this view with a positive viewpoint that emphasizes the potential role of such false attributions in the context of robotic language acquisition. By adding emotional displays and congruent body behaviors to a child-like humanoid robot's behavioral repertoire, we were able to bring naive human tutors to engage in so called intent interpretations. In developmental psychology, intent interpretations can be hypothesized to play a central role in the acquisition of emotion, volition, and similar autonomy-related words. The aforementioned experiments originally targeted the acquisition of linguistic negation. However, participants produced other affect- and motivation-related words with high frequencies too and, as a consequence, these entered the robot's active vocabulary. We will analyze participants' non-negative emotional and volitional speech and contrast it with participants' speech in a non-affective baseline scenario. Implications of these findings for robotic language acquisition in particular and artificial intelligence and robotics more generally will also be discussed.

关键词： Language acquisition developmental robotics Artificial intelligence Human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Deep unsupervised network for multimodal perception, representation and classification

引用

robotics AND AUTONOMOUS SYSTEMS 2015年 71卷 83-98页

作者： Droniou, Alain Ivaldi, Serena Sigaud, Olivier Univ Paris 06 Sorbonne Univ ISIR UMR7222 F-75005 Paris France CNRS Inst Syst Intelligents & Robot UMR7222 Paris France Tech Univ Darmstadt Intelligent Autonomous Syst Lab FB Informat Darmstadt Germany Inria F-54600 Villers Les Nancy France

In this paper, we tackle the problem of multimodal learning for autonomous robots. Autonomous robots interacting with humans in an evolving environment need the ability to acquire knowledge from their multiple perceptual channels in an unsupervised way. Most of the approaches in the literature exploit engineered methods to process each perceptual modality. In contrast, robots should be able to acquire their own features from the raw sensors, leveraging the information elicited by interaction with their environment: learning from their sensorimotor experience would result in a more efficient strategy in a life-long perspective. To this end, we propose an architecture based on deep networks, which is used by the humanoid robot iCub to learn a task from multiple perceptual modalities (proprioception, vision, audition). By structuring high-dimensional, multimodal information into a set of distinct sub-manifolds in a fully unsupervised way, it performs a substantial dimensionality reduction by providing both a symbolic representation of data and a fine discrimination between two similar stimuli. Moreover, the proposed network is able to exploit multimodal correlations to improve the representation of each modality alone. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Unsupervised learning Multimodal perception Deep learning developmental robotics

来源：评论

学校读者我要写书评

暂无评论

A hierarchical representation of behaviour supporting open ended development and progressive learning for artificial agents

引用

AUTONOMOUS ROBOTS 2021年第2期45卷 245-264页

作者： Suro, Francois Ferber, Jacques Stratulat, Tiberiu Michel, Fabien Univ Montpellier CNRS LIRMM Lab Informat Robot & Microelect Montpellier 161 Rue Ada F-34090 Montpellier France

One of the challenging aspects of open ended or lifelong agent development is that the final behaviour for which an agent is trained at a given moment can be an element for the future creation of one, or even several, behaviours of greater complexity, whose purpose cannot be anticipated. In this paper, we present modular influence network design (MIND), an artificial agent control architecture suited to open ended and cumulative learning. The MIND architecture encapsulates sub behaviours into modules and combines them into a hierarchy reflecting the modular and hierarchical nature of complex tasks. Compared to similar research, the main original aspect of MIND is the multi layered hierarchy using a generic control signal, the influence, to obtain an efficient global behaviour. This article shows the ability of MIND to learn a curriculum of independent didactic tasks of increasing complexity covering different aspects of a desired behaviour. In so doing we demonstrate the contributions of MIND to open-ended development: encapsulation into modules allows for the preservation and re-usability of all the skills acquired during the curriculum and their focused retraining, the modular structure serves the evolving topology by easing the coordination of new sensors, actuators and heterogeneous learning structures.

关键词： developmental robotics Learning agents Artificial behaviour Modular architecture Hierarchical architecture Curriculum learning

来源：评论

学校读者我要写书评

暂无评论

Temporal, Environmental, and Social Constraints of Word-Referent Learning in Young Infants: A Neurorobotic Model of Multimodal Habituation

引用

IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT 2011年第2期3卷 129-145页

作者： Veale, Richard Schermerhorn, Paul Scheutz, Matthias Indiana Univ Human Robot Interact Lab Cognit Sci Program Bloomington IN 47405 USA

Infants are able to adaptively associate auditory stimuli with visual stimuli even in their first year of life, as demonstrated by multimodal habituation studies. Different from language acquisition during later developmental stages, this adaptive learning in young infants is temporary and still very much stimulus-driven. Hence, temporal aspects of environmental and social factors figure crucially in the formation of prelexical multimodal associations. Study of these associations can offer important clues regarding how semantics are bootstrapped in real-world embodied infants. In this paper, we present a neuroanatomically based embodied computational model of multimodal habituation to explore the temporal and social constraints on the learning observed in very young infants. In particular, the model is able to explain empirical results showing that auditory word stimuli must be presented synchronously with visual stimulus movement for the two to be associated.

关键词： Artificial intelligence cognitive science developmental robotics embodied cognition neural model

来源：评论

学校读者我要写书评

暂无评论

Would Children Help a Robot in Need?

引用

INTERNATIONAL JOURNAL OF SOCIAL robotics 2011年第1期3卷 83-93页

作者： Beran, Tanya N. Ramirez-Serrano, Alejandro Kuzyk, Roman Nugent, Sarah Fior, Meghann Univ Calgary Dept Community Hlth Sci Calgary AB T2N 4N1 Canada Univ Calgary Dept Mech Engn Autonomous Reconfigurable Robot Syst Lab Calgary AB T2N 1N4 Canada Univ Calgary Dept Mech Engn Calgary AB T2N 1N4 Canada Univ Calgary Div Appl Psychol Calgary AB T2N 1N4 Canada

Just as human-human behavior and interactions are important to study, human-robot interactions will take more prominence in the near future. These interactions will not only be in one direction, robots helping humans, but they will also be bidirectional with humans helping robots. This study examined the interactions between children and robots by observing whether children help a robot complete a task, and the contexts which elicited the most help. Five studies were conducted each consisting of 20 or more children per group with an approximate even number of boys and girls. Visitors to a science centre located in a major Western Canadian city were invited to participate in an experiment set up at the centre. Their behaviors with a robot, a small 5 degree of freedom robot arm programmed with a set of predefined tasks which could be selected during the experiments, were observed. Results of chi-square analyses indicated that children are most likely to help a robot after experiencing a positive introduction to it, X-2(1) = 4.15, p = .04. Moreover, a positive introduction in combination with permission to help resulted in the vast majority (70%) of children helping. These results suggest that adult instructions about a robot impact children's perceptions and helping behaviors towards it. The generalizability of these results to children's helping behaviors towards people is also discussed.

关键词： robotics Children Prosocial behaviors developmental robotics

来源：评论

学校读者我要写书评

暂无评论

Mechanical cognitivization: a kinematic system proof of concept

引用

ADAPTIVE BEHAVIOR 2015年第3期23卷 155-170页

作者： Avigad, Gideon Li, Wei Weiss, Avi ORT Braude Coll Engn Dept Mech Engn Karmiel Israel Univ Sheffield Dept Automat Control & Syst Engn Sheffield S1 3JD S Yorkshire England

The common approach for training robots is to expose them to different environmental scenarios, training their controllers to have the best possible commands when untrained scenarios are encountered. When humans train, they do the same. They try new manipulations by performing within different environments. However, humans training also includes a type of training which, although claimed to improve cognitive capabilities, has not, to date, been adopted for the training of robots. This type of training involves the restriction of manipulation capabilities while performing different tasks, e.g. climbing with just one hand. Recently research that aims at exploring the invigorating idea that such training, termed as mechanical cognitivization (MC), would enhance the robustness of robots, has been published. However, that work has demonstrated the idea by utilizing mathematical functions. In the current paper, the first proof that such training may enhance the robustness of robots is given by using a kinematic system. Specifically, it is shown that such training improves the performances of robots when encountering the need to perform new tasks, when performing within untrained environments and when malfunctions occur. The advantages of the suggested training are highlighted through facilitating a comparison between three learning schemes that include a common neural net and two MC-based nets. These are termed here as amalgamated modes neural net and committee of modes neural net. It is shown that both MC-based schemes are superior when robustness is considered.

关键词： Cognitive robotics developmental robotics robustness

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：