Symbol Emergence in Cognitive Developmental Systems: A Survey

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to symbols. However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, second, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems.

[1]  How the Brain Got Language , 2018, Interaction Studies.

[2]  Angelo Cangelosi,et al.  Affordances in Psychology, Neuroscience, and Robotics: A Survey , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[3]  Leslie Pack Kaelbling,et al.  From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning , 2018, J. Artif. Intell. Res..

[4]  Angelo Cangelosi,et al.  Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots , 2017, Front. Neurorobot..

[5]  Tomoaki Nakamura,et al.  SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model , 2017, Front. Neurorobot..

[6]  Emre Ugur,et al.  Emergent Structuring of Interdependent Affordance Learning Tasks Using Intrinsic Motivation and Empirical Feature Selection , 2017, IEEE Transactions on Cognitive and Developmental Systems.

[7]  Kuniyuki Takahashi,et al.  Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Tatsuya Kawahara,et al.  Detection of social signals for recognizing engagement in human-robot interaction , 2017, ArXiv.

[9]  Justus H. Piater,et al.  Computational models of affordance in robotics: a taxonomy and systematic classification , 2017, Adapt. Behav..

[10]  Tomoaki Nakamura,et al.  Online Algorithm for Robots to Learn Object Concepts and Language Model , 2017, IEEE Transactions on Cognitive and Developmental Systems.

[11]  Angelo Cangelosi,et al.  Communication with Speech and Gestures: Applications of Recurrent Neural Networks to Robot Language Learning , 2017 .

[12]  Mohit Shridhar,et al.  Grounding Spatio-Semantic Referring Expressions for Human-Robot Interaction , 2017, ArXiv.

[13]  Benjamin Rosman,et al.  Hierarchy Through Composition with Multitask LMDPs , 2017, ICML.

[14]  Demis Hassabis,et al.  Grounded Language Learning in a Simulated 3D World , 2017, ArXiv.

[15]  Tadahiro Taniguchi,et al.  Online spatial concept and lexical acquisition with simultaneous localization and mapping , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[16]  Stefan Wermter,et al.  Interactive natural language acquisition in a multi-modal recurrent neural architecture , 2017, Connect. Sci..

[17]  J. Tani.  Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-Organizing Dynamic Phenomena , 2016 .

[18]  Tao Mei,et al.  Video Captioning with Transferred Semantic Attributes , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Dustin Tran,et al.  Edward: A library for probabilistic modeling, inference, and criticism , 2016, ArXiv.

[20]  A. Holtmaat,et al.  Functional and structural underpinnings of neuronal assembly formation in learning , 2016, Nature Neuroscience.

[21]  Sergio Gomez Colmenarejo,et al.  Hybrid computing using a neural network with dynamic external memory , 2016, Nature.

[22]  Tomoaki Nakamura,et al.  Online joint learning of object concepts and language model using multimodal hierarchical Dirichlet process , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  D. Hanuš,et al.  Causal reasoning versus associative learning: A useful dichotomy or a strawman battle in comparative psychology? , 2016, Journal of comparative psychology.

[24]  Alexandre Bernardino,et al.  From human instructions to robot actions: Formulation of goals, affordances and probabilistic planning , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[25]  A. Nieder.  The neuronal code for number , 2016, Nature Reviews Neuroscience.

[26]  R. Sun.  Anatomy of the Mind: Exploring Psychological Mechanisms and Processes with the Clarion Cognitive Architecture , 2016 .

[27]  Tadahiro Taniguchi,et al.  Double articulation analyzer with deep sparse autoencoder for unsupervised word discovery from speech signals , 2016, Adv. Robotics.

[28]  Ryan P. Adams,et al.  Composing graphical models with neural networks for structured representations and fast inference , 2016, NIPS.

[29]  Tadahiro Taniguchi,et al.  Spatial Concept Acquisition for a Mobile Robot That Integrates Self-Localization and Unsupervised Word Discovery From Spoken Sentences , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[30]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[31]  Pravesh Ranchod,et al.  Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[32]  Masahide Kaneko,et al.  Concept formation by robots using an infinite mixture of models , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[33]  Justus H. Piater,et al.  Refining discovered symbols with multi-step interaction experience , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[34]  Pierre-Yves Oudeyer,et al.  MCA-NMF: Multimodal Concept Acquisition with Non-Negative Matrix Factorization , 2015, PloS one.

[35]  Tae-Kyun Kim,et al.  STARE: Spatio-Temporal Attention Relocation for Multiple Structured Activities Detection , 2015, IEEE Transactions on Image Processing.

[36]  Tomoaki Nakamura,et al.  Symbol emergence in robotics: a survey , 2015, Adv. Robotics.

[37]  Luc Steels,et al.  The Talking Heads experiment: Origins of words and meanings , 2015 .

[38]  Leslie Pack Kaelbling,et al.  Symbol Acquisition for Probabilistic High-Level Planning , 2015, IJCAI.

[39]  Tadahiro Taniguchi,et al.  Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition From Continuous Speech Signals , 2015, IEEE Transactions on Cognitive and Developmental Systems.

[40]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[41]  Justus H. Piater,et al.  Bottom-up learning of object categories, action effects and logical rules: From continuous manipulative exploration to symbolic planning , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[42]  Christopher W. Geib,et al.  Structural Bootstrapping—A Novel, Generative Mechanism for Faster and More Efficient Acquisition of Action-Knowledge , 2015, IEEE Transactions on Autonomous Mental Development.

[43]  T. Callaghan,et al.  The Development of Symbolic Representation , 2015 .

[44]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[45]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[46]  Alex Graves,et al.  Neural Turing Machines , 2014, ArXiv.

[47]  G. Palm,et al.  Cell assemblies in the cerebral cortex , 2014, Biological Cybernetics.

[48]  Tomoaki Nakamura,et al.  Mutual learning of an object concept and language model based on MLDA and NPYLM , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[49]  Leslie Pack Kaelbling,et al.  Constructing Symbolic Representations for High-Level Planning , 2014, AAAI.

[50]  E. Bates,et al.  The Emergence of Symbols: Cognition and Communication in Infancy , 2014 .

[51]  Jun Tani,et al.  Self-Organization and Compositionality in Cognitive Brains: A Neurorobotics Study , 2014, Proceedings of the IEEE.

[52]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[53]  Yoshiki Ando,et al.  Formation of hierarchical object concept using hierarchical latent Dirichlet allocation , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[54]  Silvia Coradeschi,et al.  A Short Review of Symbol Grounding in Robotic and Intelligent Systems , 2013, KI - Künstliche Intelligenz.

[55]  Jos Elfring,et al.  Semantic world modeling using probabilistic multiple hypothesis anchoring , 2013, Robotics Auton. Syst..

[56]  Tomoaki Nakamura,et al.  Online learning of concepts and words using multimodal LDA and hierarchical Pitman-Yor Language Model , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[57]  Emre Ugur,et al.  Self-discovery of motor primitives and learning grasp affordances , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[58]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[59]  Rachid Alami,et al.  A Human-Aware Manipulation Planner , 2012, IEEE Transactions on Robotics.

[60]  Luke S. Zettlemoyer,et al.  A Joint Model of Language and Perception for Grounded Attribute Learning , 2012, ICML.

[61]  Michael Beetz,et al.  Grounding the Interaction: Anchoring Situated Discourse in Everyday Human-Robot Interaction , 2012, Int. J. Soc. Robotics.

[62]  H. Damasio,et al.  Understanding otherness: the neural bases of action comprehension and pain empathy in a congenital amputee. , 2012, Cerebral cortex.

[63]  Benjamin Kuipers,et al.  Autonomous Learning of High-Level States and Actions in Continuous Environments , 2012, IEEE Transactions on Autonomous Mental Development.

[64]  Yiannis Aloimonos,et al.  The minimalist grammar of action , 2012, Philosophical Transactions of the Royal Society B: Biological Sciences.

[65]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[66]  Matthew R. Walter,et al.  Approaching the Symbol Grounding Problem with Probabilistic Graphical Models , 2011, AI Mag..

[67]  Tomoaki Nakamura,et al.  Multimodal categorization by hierarchical dirichlet process , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[68]  Mark Steedman,et al.  Object-Action Complexes: Grounded abstractions of sensory-motor processes , 2011, Robotics Auton. Syst..

[69]  M. Arbib.  From Mirror Neurons to Complex Imitation in the Evolution of Language and Tool Use , 2011 .

[70]  Matthew R. Walter,et al.  Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation , 2011, AAAI.

[71]  Raymond J. Mooney,et al.  Learning to Interpret Natural Language Navigation Instructions from Observations , 2011, Proceedings of the AAAI Conference on Artificial Intelligence.

[72]  Tomoaki Nakamura,et al.  Bag of multimodal LDA models for concept formation , 2011, 2011 IEEE International Conference on Robotics and Automation.

[73]  Takayuki Nagai,et al.  Robots that Learn to Communicate: A Developmental Approach to Personally and Physically Situated Human-Robot Conversations , 2010, AAAI Fall Symposium: Dialog with Robots.

[74]  Marc Toussaint,et al.  Planning with Noisy Probabilistic Relational Rules , 2010, J. Artif. Intell. Res..

[75]  Frederic Py,et al.  A systematic agent framework for situated autonomous systems , 2010, AAMAS.

[76]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[77]  Tomoaki Nakamura,et al.  Grounding of word meanings in multimodal concepts using LDA , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[78]  M. Kawato,et al.  Shared neural correlates for language and tool use in Broca's area , 2009, Neuroreport.

[79]  Koji Fujita,et al.  A Prospect for Evolutionary Adequacy: Merge and the Evolution and Development of Human Language , 2009, Biolinguistics.

[80]  Matthias Scheutz,et al.  What to do and how to do it: Translating natural language directives into temporal and dynamic logic representation for goal management and action execution , 2009, 2009 IEEE International Conference on Robotics and Automation.

[81]  Masaki Ogino,et al.  Cognitive Developmental Robotics: A Survey , 2009, IEEE Transactions on Autonomous Mental Development.

[82]  Florentin Wörgötter,et al.  Cognitive agents - a procedural perspective relying on the predictability of Object-Action-Complexes (OACs) , 2009, Robotics Auton. Syst..

[83]  M. Tomasello.  The usage-based theory of language acquisition , 2009 .

[84]  Ron Sun,et al.  The Cambridge Handbook of Computational Psychology , 2008 .

[85]  Derek C. Penn,et al.  Causal cognition in human and nonhuman animals: a comparative, critical review. , 2007, Annual review of psychology.

[86]  S. Laurence,et al.  The ontology of concepts: Abstract objects or mental representations? , 2007 .

[87]  O. Khatib,et al.  Springer Handbook of Robotics , 2008 .

[88]  J. Mandler.  On the origins of the conceptual system. , 2007, The American psychologist.

[89]  Tomoaki Nakamura,et al.  Multimodal object categorization by a robot , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[90]  Naoto Iwahashi,et al.  Robots That Learn Language: A Developmental Approach to Situated Human-Robot Conversations , 2007 .

[91]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[92]  L. P. Kaelbling,et al.  Learning Symbolic Models of Stochastic Domains , 2007, J. Artif. Intell. Res..

[93]  Rolf Pfeifer,et al.  How the body shapes the way we think - a new view on intelligence , 2006 .

[94]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[95]  Angelo Cangelosi,et al.  An Embodied Model for Sensorimotor Grounding and Grounding Transfer: Experiments With Epigenetic Robots , 2006, Cogn. Sci..

[96]  Mariarosaria Taddeo,et al.  Solving the symbol grounding problem: a critical review of fifteen years of research , 2005, J. Exp. Theor. Artif. Intell..

[97]  G. Rizzolatti.  The mirror neuron system and its function in humans , 2005, Anatomy and Embryology.

[98]  G. Rizzolatti,et al.  Parietal Lobe: From Action Organization to Intention Understanding , 2005, Science.

[99]  M. Tomasello.  Constructing a Language , 2005 .

[100]  Yoshihiko Nakamura,et al.  Design of the continuous symbol space for the intelligent robots using the dynamics-based information processing , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[101]  J. Deloache.  Becoming symbol-minded , 2004, Trends in Cognitive Sciences.

[102]  G. Rizzolatti,et al.  Both of Us Disgusted in My Insula The Common Neural Basis of Seeing and Feeling Disgust , 2003, Neuron.

[103]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[104]  Margaret Wilson,et al.  Six views of embodied cognition , 2002, Psychonomic bulletin & review.

[105]  Paul Vogt,et al.  The physical symbol grounding problem , 2002, Cognitive Systems Research.

[106]  G. Murphy,et al.  The Big Book of Concepts , 2002 .

[107]  Doina Precup,et al.  Learning Options in Reinforcement Learning , 2002, SARA.

[108]  F. Dick,et al.  Language, gesture, and the developing brain. , 2002, Developmental psychobiology.

[109]  T. Callaghan,et al.  Emergence of graphic symbol functioning and the question of domain specificity: a longitudinal training study. , 2002, Child development.

[110]  Daniel Chandler,et al.  Semiotics: The Basics , 2001 .

[111]  James F. Allen,et al.  Toward Conversational Human-Computer Interaction , 2001, AI Mag..

[112]  G. Rizzolatti,et al.  I Know What You Are Doing A Neurophysiological Study , 2001, Neuron.

[113]  J. Stevenson.  The cultural origins of human cognition , 2001 .

[114]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[115]  Angelo Cangelosi,et al.  From robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories1 , 2000, Connect. Sci..

[116]  T. Callaghan.  Factors affecting children's graphic symbol use in the third year , 2000 .

[117]  P. Rochat,et al.  Do young children use objects as symbols , 1999 .

[118]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[119]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[120]  P. Willatts,et al.  Development of means-end behavior in young infants: pulling a support to retrieve a distant object. , 1999, Developmental psychology.

[121]  Stefano Nolfi,et al.  Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems , 1998, Neural Networks.

[122]  M. Arbib,et al.  Language within our grasp , 1998, Trends in Neurosciences.

[123]  P. Greenfield,et al.  Toward a neurology of grammar , 1998, Behavioral and Brain Sciences.

[124]  G. Rizzolatti,et al.  Action recognition in the premotor cortex. , 1996, Brain : a journal of neurology.

[125]  G. Rizzolatti,et al.  Premotor cortex and the recognition of motor actions. , 1996, Brain research. Cognitive brain research.

[126]  R. Sutton,et al.  Advances in Neural Information Processing Systems pp MIT Press Generalization in Reinforcement Learning Successful Examples Using Sparse Coarse Coding , 2010 .

[127]  Gerald Tesauro,et al.  Temporal difference learning and TD-Gammon , 1995, CACM.

[128]  Andy Clark,et al.  Doing without representing? , 1994, Synthese.

[129]  J. Deloache.  Symbolic functioning in very young children: understanding of pictures and models. , 1991, Child development.

[130]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[131]  S. Harnad.  Symbol grounding problem , 1990, Scholarpedia.

[132]  P. Willatts.  The stage-IV infant's solution of problems requiring the use of supports** , 1984 .

[133]  M. Swanwick,et al.  Early language development. , 1984, Nursing.

[134]  L. Barsalou,et al.  Ad hoc categories , 1983, Memory & cognition.

[135]  Allen Newell,et al.  Physical Symbol Systems , 1980, Cogn. Sci..

[136]  Kevin P. Jones,et al.  Informatics , 1976, Nature.

[137]  P. L. Adams.  THE ORIGINS OF INTELLIGENCE IN CHILDREN , 1976 .

[138]  K. Glaser.  The Origins of Intelligence in Children , 1964 .

[139]  Erin J Rotheram-Fuller.  Symbolic Thought , 2021, Encyclopedia of Autism Spectrum Disorders.

[140]  Ursula Hess,et al.  Handbook of Categorization in Cognitive Science , 2017 .

[141]  Philipp Koehn,et al.  Cognitive Psychology , 1992, Ageing and Society.

[142]  T. Lillicrap,et al.  Under review as a conference paper at ICLR 2017 D ISCOVERING OBJECTS AND THEIR RELATIONS FROM ENTANGLED SCENE REPRESENTATIONS , 2016 .

[143]  Luke S. Zettlemoyer,et al.  Learning to Parse Natural Language Commands to a Robot Control System , 2012, ISER.

[144]  Tomoki Toda,et al.  An Extended Mobile Manipulation Robot Learning Novel Objects , 2012 .

[145]  Mikio Nakano,et al.  Learning Place-Names from Spoken Utterances and Localization Results by Mobile Robot , 2011, INTERSPEECH.

[146]  L. Steels.  The symbol grounding problem has been solved, so what’s next? , 2008 .

[147]  M. Tomasello.  Origins of human communication , 2008 .

[148]  Katerina Pastra.  PRAXICON : The Development of a Grounding Resource , 2008 .

[149]  John R. Anderson,et al.  Constraints in Cognitive Architectures , 2008 .

[150]  Max Lungarella,et al.  Developmental Robotics , 2009, Encyclopedia of Artificial Intelligence.

[151]  A. Cangelosi.  The grounding and sharing of symbols , 2006 .

[152]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[153]  G. Rizzolatti,et al.  Understanding motor events: a neurophysiological study , 2004, Experimental Brain Research.

[154]  M. Tomasello.  On the Different Origins of Symbols and Grammar , 2003 .

[155]  Yasuo Kuniyoshi,et al.  From Humanoid Embodiment to Theory of Mind , 2003, Embodied Artificial Intelligence.

[156]  Sridhar Mahadevan,et al.  Recent Advances in Hierarchical Reinforcement Learning , 2003, Discret. Event Dyn. Syst..

[157]  Luc Steels,et al.  Grounding symbols through evolutionary language games , 2002 .

[158]  K. Dautenhahn,et al.  The Mirror System, Imitation, and the Evolution of Language , 1999 .

[159]  P. V. Loocke.  The Nature of Concepts : Evolution, Structure and Representation , 1999 .

[160]  R. D. Kavanaugh,et al.  The depiction of imaginary transformations: Early comprehension of a symbolic function , 1997 .

[161]  M. Arbib,et al.  Neural expectations : A possible evolutionary path from manual skills to language , 1996 .

[162]  L. Adamson.  Communication Development During Infancy , 1995 .

[163]  Chris Sinha,et al.  Symbol Grounding or the Emergence of Symbols? Vocabulary Growth in Children and a Connectionist Net , 1992 .

[164]  Charles T. Meadow,et al.  Relevance? , 1985, J. Am. Soc. Inf. Sci..

[165]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[166]  G Rosolato,et al.  Symbol formation. , 1978, The International journal of psycho-analysis.

[167]  H. Simon,et al.  Completer Science asEmp rical Inquiry: Symbols and Search , 1976 .

[168]  John Maynard Keynes,et al.  The Collected Writings , 1971 .

[169]  J. Piaget.  Play, dreams and imitation in childhood , 1951 .

[170]  A. Krizhevsky.  ImageNet Classification with Deep Convolutional Neural Networks , 2022 .