Showing papers on "Cognitive robotics published in 1999"
TL;DR: A number of critical questions are raised concerning the nature and scope of the nature of this approach to embodiment, drawing a distinction between two kinds of appeal to embodiment.
571 citations
Book•
02 Jul 1999TL;DR: This book represents Rodney A. Brooks' initial formulation of and contributions to the development of the behavior-based approach to robotics and presents all of the key philosophical and technical ideas that put this "bottom-up" approach at the forefront of current research in not only AI but all of cognitive science.
Abstract: Until the mid-1980s, AI researchers assumed that an intelligent system doing high-level reasoning was necessary for the coupling of perception and action. In this traditional model, cognition mediates between perception and plans of action. Realizing that this core AI, as it was known, was illusory, Rodney A. Brooks turned the field of AI on its head by introducing the behavior-based approach to robotics. The cornerstone of behavior-based robotics is the realization that the coupling of perception and action gives rise to all the power of intelligence and that cognition is only in the eye of an observer. Behavior-based robotics has been the basis of successful applications in entertainment, service industries, agriculture, mining, and the home. It has given rise to both autonomous mobile robots and more recent humanoid robots such as Brooks' Cog. This book represents Brooks' initial formulation of and contributions to the development of the behavior-based approach to robotics. It presents all of the key philosophical and technical ideas that put this "bottom-up" approach at the forefront of current research in not only AI but all of cognitive science.
550 citations
TL;DR: In this article, the authors argue that the nature of situated learning and cognition cannot be fully understood by focusing only on social, cultural and contextual factors, and use conceptual metaphor theory to show how embodied cognition, while providing grounding for situatedness, also gives fruitful results in analyzing the cognitive difficulties underlying the understanding of continuity.
Abstract: In this paper we analyze, from the perspective of 'Embodied Cognition', why learning and cognition are situated and context-dependent. We argue that the nature of situated learning and cognition cannot be fully understood by focusing only on social, cultural and contextual factors. These factors are themselves further situated and made comprehensible by the shared biology and fundamental bodily experiences of human beings. Thus cognition itself is embodied, and the bodily-grounded nature of cognition provides a foundation for social situatedness, entails a reconceptualization of cognition and mathematics itself, and has important consequences for mathematics education. After framing some theoretical notions of embodied cognition in the perspective of modern cognitive science, we analyze a case study – continuity of functions. We use conceptual metaphor theory to show how embodied cognition, while providing grounding for situatedness, also gives fruitful results in analyzing the cognitive difficulties underlying the understanding of continuity.
313 citations
TL;DR: The strategy will be to argue from within a general framework that accepts many of the basic premises of the work (in new robotics and in dynamical systems theory) that motivates such scepticism in the first place.
Abstract: There is a definite challenge in the air regarding the pivotal notion of internal representation. This challenge is explicit in, e.g., van Gelder, 1995; Beer, 1995; Thelen & Smith, 1994; Wheeler, 1994; and elsewhere. We think it is a challenge that can be met and that (importantly) can be met by arguing from within a general framework that accepts many of the basic premises of the work (in new robotics and in dynamical systems theory) that motivates such scepticism in the first place. Our strategy will be as follows. We begin (Section 1) by offering an account (an example and something close to a definition) of what we shall term Minimal Robust Representationalism (MRR). Sections 2 & 3 address some likely worries and questions about this notion. We end (Section 4) by making explicit the conditions under which, on our account, a science (e.g., robot ics) may claim to be addressing cognitive phenomena.
229 citations
01 Jan 1999
TL;DR: The authors argue for a distinction between the classical view of referential representation and the alternative concept of system-relative representation, which refers to situated cognitive processes whose dynamics are merely modulated by their environment rather than being instructed and determined by it.
Abstract: This paper discusses the notion of representation and outlines the ideas and questions which led to the organization of this volume. We argue for a distinction between the classical view of referential representation, and the alternative concept of system-relative representation. The latter refers to situated cognitive processes whose dynamics are merely modulated by their environment rather than being instructed and determined by it.
129 citations
TL;DR: A prominent robotics professor surprised me at last year's RSJ conference: ''There isn't really a symbol grounding problem for robotics, is there? I often ask people, 'Is symbol grounding a problem for your re search?' and no one says, 'Yes.' '' Sensing irony in his voice, I replied, ''That's because no one is building sys tems with a human or even vertebrate level of competence. When they try to, they may respond to your question differently as mentioned in this paper.
Abstract: A prominent robotics professor surprised me at last year's RSJ conference: \"There isn't really a symbol grounding problem for robotics, is there? I often ask people, 'Is symbol grounding a problem for your re search?' and no one says, 'Yes.' \" Sensing irony in his voice, I replied, \"That's because no one is building sys tems with a human or even vertebrate level of competence. When they try to, they may respond to your question differently.\" Harnad (1990) identified the symbol grounding prob lem as a problem of embodying symbol systems
49 citations
06 Sep 1999
TL;DR: It is argued that the framework proposed by Vygotsky provides a promising research direction in autonomous agents and demonstrates how a teacher-learner setup can be used to teach a robot a proto-language.
Abstract: The paper discusses two prominent theories of cognitive development and relates them to experiments in social robotics. The main difference between these theories lies in the different views on the relationship between a child and its social environment: a) the child as a solitary thinker (Piaget) and b) the child in society (Vygotsky). We discuss the implications this has on the design of socially intelligent agents, focusing on robotic agents. We argue that the framework proposed by Vygotsky provides a promising research direction in autonomous agents. We give examples of implementations in the area of social robotics which support our theoretical considerations. More specifically, we demonstrate how a teacher-learner setup can be used to teach a robot a proto-language. The same control architecture is also used for a humanoid doll robot which can interact with a human by imitation. Another experiment addresses dynamic coupling of movements between a human and a mobile robot. Here, emergent robot-human interaction dynamics are influenced by the temporal coordination between the robot's and the human's movements.
47 citations
Journal Article•
TL;DR: The situated view on cognition will also be central for future developments of man-machine interaction, in particular in educational tools that exploit information technology.
Abstract: With the development of computers in the 1940s and 1950s, a new model for human thinking became available. The initial period of cognitive science was driven by the analogy that the brain functions like a computer. Consequently, thinking was viewed as the processing of symbols. This was also the methodology of classical artificial intelligence. As a result of criticism of the symbol manipulation paradigm, there have recently been two main kinds of reaction to it. The first one is connectionism, where thinking is modelled as associations in artificial neuron networks. Some connectionist models are tightly connected to developments in the neurosciences, while others are more general models of cognitive processes such as concept formation. The second reaction consists of theories of embodied and situated cognition, where cognition is seen as taking place not only in the brain, but in interaction with the body and the surrounding world. In line with this, modern studies of robotics are based on so called reactive systems, the actions of which depend directly on the world instead of a symbolic model of it. The situated view on cognition will also be central for future developments of man-machine interaction, in particular in educational tools that exploit information technology.
27 citations
TL;DR: A definition of cognition in terms of the complexity of behavior it subserves is presented, supported by two types of empirical evidence: robot experiments show that the simple mechanisms are in fact sufficient to produce cognitive behavior, while behavioral experiments indicate that stereotyped and cognitive mechanisms co-exist in human spatial behavior.
Abstract: Spatial cognition is a cognitive ability that arose relatively early in animal evolution. It is therefore very well suited for studying the evolution from stereotyped to cognitive behavior and the general mechanisms underlying cognitive abilities. This paper presents a definition of cognition in terms of the complexity of behavior it subserves. This approach allows questions about the mechanisms of cognition, just as the mechanisms of simpler behavior have been addressed in neuroethology. As an example for this mechanistic view of cognitive abilities, the view-graph theory of cognitive maps will be discussed. It will be argued that spatial cognitive abilities can be explained by scaling up simple, stereotyped mechanisms of spatial behavior. This evolutionary view of cognition is supported by two types of empirical evidence: robot experiments show that the simple mechanisms are in fact sufficient to produce cognitive behavior, while behavioral experiments with subjects exploring a computer graphics environment indicate that stereotyped and cognitive mechanisms co-exist in human spatial behavior.
25 citations
TL;DR: This paper describes a research program about how to achieve artificial intelligence by building robots that is part of the behavior-oriented AI approach, but differs in some of its hypotheses and methodological approach.
Abstract: This paper describes a research program about how to achieve artificial intelligence by building robots It is part of the behavior-oriented AI approach, but differs in some of its hypotheses and methodological approach
22 citations
TL;DR: This paper argues that the term “robotics” needs to be redefined as “the science of extending human motor capabilities with machines,” and uses the author’s experience with robotics over the past 25 years to support this argument.
Abstract: This paper argues that the term “robotics” needs to be redefined as “the science of extending human motor capabilities with machines,” and uses the author’s experience with robotics over the past 2...
01 Jan 1999
TL;DR: The paper argues that these properties can be achieved in cognitive models by a combination of emergent computation and computational dynamics, and discusses the possibilities of building such models on the basis of DUAL — a distributed cognitive architecture.
Abstract: Human cognitive processes exhibit three important qualities: flexibility, efficiency, and context sensitivity. The paper argues that these properties can be achieved in cognitive models by a combination of emergent computation and computational dynamics. We discuss the possibilities of building such models on the basis of DUAL — a distributed cognitive architecture. Computation in DUAL emerges from the collective behaviour of a great number of specialised agents running in parallel and interacting through a network of relations. The agents work at individual speeds reflecting their relevance to the context. Moreover, new agents and new relations can be created in the course of computation. In this way the particular set of agents engaged in a cognitive task and the pattern of their interaction is formed dynamically. An example of such dynamic emergent computation — mapping between two symbolic structures — is discussed in more detail.
01 Jan 1999
TL;DR: In this article, the authors argue for the viability of an answer based on a rigorous, logical account of interleaved perception, planning and action in a mobile robot controller, and a number of common criticisms of approaches in this style are reviewed.
Abstract: This paper addresses the question of what sort of computation should be used to mediate between perception and action in a mobile robot. Drawing on recent work in the area of cognitive robotics, the paper argues for the viability of an answer based on a rigorous, logical account of interleaved perception, planning and action. In addition, a number of common criticisms of approaches in this style are reviewed, and an implemented logicbased robot controller is described.
08 Nov 1999
TL;DR: This work describes a framework for control of attention and for pattern categorization using a robot platform consisting of an articulated stereo-head with four degrees of freedom, capable of analyzing all regions of its world, selected according to a salience map.
Abstract: This work describes a framework for control of attention and for pattern categorization using a robot platform consisting of an articulated stereo-head with four degrees of freedom (pan, tilt, left verge, and right verge). As a practical result of this work, the system can select a region of interest, perform attention shifts involving saccadic movements, perform efficient feature extraction and recognition, incrementally construct a world map, and keep the map consistent with a current perception of the world. Another important result for the attentional mechanism is that the system is capable of analyzing all regions of its world, selected according to a salience map.
TL;DR: A formal common sense theory of the adoption of perception-based beliefs is presented and an abstract architecture for an agent which is both embodied and capable of reasoning is given and this is related to the concrete architectures of two vision-based surveillance systems.
Abstract: In this paper we present a formal common sense theory of the adoption of perception-based beliefs. We begin with a logical analysis of perception and then consider when perception should lead to belief change. Our theory is intended to apply to perception in humans and to perception in artificial agents at the level of the symbolic interface between a vision system and a belief system. In order to provide a context for our work we relate it to the emerging field of cognitive robotics, give an abstract architecture for an agent which is both embodied and capable of reasoning, and relate this to the concrete architectures of two vision-based surveillance systems.
01 Jan 1999
TL;DR: This work advocates a procedure for cognitive modeling that uses an integrative cognitive architecture, prior models in that architecture, and a relatively small data set, to gain general insights about a larger domain of interest, and demonstrates this procedure by examining the development of a Soar model of learning and memory in a real-world humancomputer interaction task.
Abstract: An integrative cognitive architecture provides a computational framework within which to model a broad range of human behavior. It encompasses behavior from perception through cognition to motor action, and integrates performance, learning, and eventually moderator variables like cultural values or fatigue. To model any one behavioral data set using an integrative cognitive architecture can be more bother than it seems to be worth. However, integrative cognitive architectures provide power and constraint to every model, benefits that we believe offset the cost of “architecture overhead”. We advocate a procedure for cognitive modeling that uses an integrative cognitive architecture, prior models in that architecture, and a relatively small data set, to gain general insights about a larger domain of interest. We demonstrate this procedure by examining the development of a Soar model of learning and memory in a real-world humancomputer interaction task.
17 Oct 1999
TL;DR: The paper addresses the open question of robots which act as humans by implementing a basic robotic motor task using anthropomorphic hardware and an anthropomorphic computational approach and suggests that similar performance can be achieved by the formal mathematical model of reinforcement learning and by the locally bio-mimetic architecture.
Abstract: If we could obtain robots which act as humans, does this imply that both have the same structure and are made of the same "substance"? The paper addresses this open question by implementing a basic robotic motor task using anthropomorphic hardware and an anthropomorphic computational approach. Two different algorithms implementing reinforcement learning both at a psychological and bio-mimetic level are presented and discussed. The performance achieved during the experimental trials suggests that similar performance can be achieved by the formal mathematical model of reinforcement learning and by the locally bio-mimetic architecture. This is very promising for the achievement of the adaptability, versatility and flexibility required of a humanoid, whilst still at acceptable levels of computational burden.
01 Jan 1999
18 Oct 1999
TL;DR: The design of a data fusion module for skill transfer applications consists of two independent modules for optimal fusion and filtering, and a different interpretation of the Kalman filter equations is made, in order to achieve a "model-free" equation that is capable of following arbitrary variables.
Abstract: In modern robotics, the robot is seen not as a mechanical unit, but instead as an intelligent unit, with planning and cognitive structures that are capable of making intelligent decisions and of helping human beings in high-level and interactive tasks. A new generation of robots is ready to emerge: human-oriented robots. In the near future, they should be able to perform perfect human-robot symbiosis, such as helping disabled people in their basic day-to-day problems. A key issue to accomplish this goal is the development of robust skill transfer systems, in order to teach some basic tasks in a natural way. This paper describes the design of a data fusion module for skill transfer applications. It consists of two independent modules for optimal fusion and filtering. A different interpretation of the Kalman filter equations is made, in order to achieve a "model-free" equation that is capable of following arbitrary variables. The presented fusion algorithm is global, and could easily be extended to any arbitrary system. It was successfully tested in the Institute of Robotics and System Dynamics at the German Aerospace Centre (DLR).
TL;DR: In this article, the authors proposed a method to solve the problem of "missing links" by using a set of keywords: "unknown", "unknown" and "unknown unknown" keywords.
Abstract: 昨年7月パリで開催された第2回ロボカップ国際大会で は,世界22カ国から約70チームが参加し,シミュレーショ ン (約40チーム),実機小型 (12チーム),実機中型 (18チー ム) の3つのリーグで熱戦が繰り広げられた.ロボカップ の目的は,ロボティクスと人工知能における新たな標準問 題を設定し,多くの研究者が動的マルチエージェント環境 における協調・競合問題の解決に当たることで,知的人工 システムの様々な諸問題を解決することである [1]. 筆者のチームは,第1回の名古屋大会から参加し,特徴 として学習機能を取り上げ,主に強化学習法を用いてロ ボットの行動を獲得してきた.通常,「学習」の特徴として あげられる (1)容易なプログラミング (2)より少ない事前知識 (3)汎用性 は,理論的な学習アルゴリズムが理想的な環境で適用さ れる際には,優れた特徴と写るが,実際の環境に適用して いく上では,必ずしもそうとは限らない.我々の研究目標 は,このような表層的な学習の特徴の実現より,むしろ自 律エージェントが環境との相互作用を通して,世界をどの ように表現し行動を獲得していくかといった,ロボットの 認知過程に焦点を当ててきた.特に,環境因子として他の エージェントの行動が自分の行動をどのように規定してい くかという過程の中に,ロボットが「自我」を見出してい く道筋が解釈できるのではないかという期待がある. 本稿では,我々のここ5年間の研究の推移を認知ロボティ クスの観点から見直す.最初に他者の存在の認知に関する 議論を展開する.次にそれぞれのアプローチについて,筆 者が「展望」[2]でのべた二つの設計論 (内部/外部構造の設