Abstract Concept Learning in Cognitive Robots

Understanding 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. For 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. There 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.

[1]  Minoru Asada,et al.  Modeling Early Vocal Development Through Infant–Caregiver Interaction: A Review , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[2]  Philippe Gaussier,et al.  Autonomous Cognitive Robots Need Emotional Modulations: Introducing the eMODUL Model , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[3]  Emiliano Lorini,et al.  Computational Modeling of Emotion: Toward Improving the Inter- and Intradisciplinary Exchange , 2013, IEEE Transactions on Affective Computing.

[4]  Penny M. Pexman,et al.  The role of embodiment in conceptual development , 2019 .

[5]  Paul D. Siakaluk,et al.  Situated conceptualization and semantic processing: effects of emotional experience and context availability in semantic categorization and naming tasks , 2015, Psychonomic bulletin & review.

[6]  Michael A. Arbib,et al.  Who Needs Emotions? - The brain meets the robot , 2004, Who Needs Emotions?.

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

[8]  Angelo Cangelosi,et al.  A review of abstract concept learning in embodied agents and robots , 2018, Philosophical Transactions of the Royal Society B: Biological Sciences.

[9]  Ning Wang,et al.  The multi-modal interface of Robot-Era multi-robot services tailored for the elderly , 2017, Intelligent Service Robotics.

[10]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[11]  Alessandro G. Di Nuovo,et al.  An embodied model for handwritten digits recognition in a cognitive robot , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[12]  Dedre Gentner,et al.  Metaphoric extension, relational categories, and abstraction , 2019 .

[13]  R. Bevilacqua,et al.  Acceptance of Robot-Era system: results of robotic services in smart environments with older adults , 2018 .

[14]  L. Barsalou,et al.  Situating Abstract Concepts , 2004 .

[15]  Lawrence W Barsalou,et al.  Abstraction in perceptual symbol systems. , 2003, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[16]  Alessandro G. Di Nuovo,et al.  Long-Short Term Memory Networks for Modelling Embodied Mathematical Cognition in Robots , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[17]  Elizabet Spaepen,et al.  Approximate number word knowledge before the cardinal principle. , 2015, Journal of experimental child psychology.

[18]  Brian Scassellati,et al.  Socially Assistive Robotics: Methods and Implications for the Future of Work and Care , 2022, Robophilosophy.

[19]  S. Cappa,et al.  The neural representation of abstract words: the role of emotion. , 2014, Cerebral cortex.

[20]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[21]  Frank Domahs,et al.  Mind the gap between both hands: Evidence for internal finger-based number representations in children's mental calculation , 2008, Cortex.

[22]  A. Cangelosi,et al.  Temporal patterns in multi-modal social interaction between elderly users and service robot , 2019, Interaction Studies.

[23]  Angelo Cangelosi,et al.  The iCub learns numbers: An embodied cognition study , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[24]  Angelo Cangelosi,et al.  Grounding fingers, words and numbers in a cognitive developmental robot , 2014, 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB).

[25]  Nicholas Roy,et al.  Efficient grounding of abstract spatial concepts for natural language interaction with robot platforms , 2018, Int. J. Robotics Res..

[26]  Neil D. Lawrence,et al.  Memory and mental time travel in humans and social robots , 2019, Philosophical Transactions of the Royal Society B.

[27]  Angelo Cangelosi,et al.  The grounding of higher order concepts in action and language: A cognitive robotics model , 2012, Neural Networks.

[28]  D Feil-Seifer,et al.  Socially Assistive Robotics , 2011, IEEE Robotics & Automation Magazine.

[29]  S. Dehaene.  Varieties of numerical abilities , 1992, Cognition.

[30]  Alessandro Di Nuovo,et al.  A Developmental Neuro-Robotics Approach for Boosting the Recognition of Handwritten Digits , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[31]  Gabriella Vigliocco,et al.  The Role of Sensory and Motor Information in Semantic Representation: A Review , 2008 .

[32]  Luis-Felipe Rodríguez,et al.  Computational models of emotions for autonomous agents: major challenges , 2012, Artificial Intelligence Review.

[33]  Angelo Cangelosi,et al.  Making sense of words: a robotic model for language abstraction , 2016, Autonomous Robots.

[34]  Daniela Conti,et al.  “Robot, tell me a tale!” , 2020 .

[35]  Alex Graves,et al.  Long Short-Term Memory , 2020, Computer Vision.

[36]  Alessandro Di Nuovo,et al.  Development of numerical cognition in children and artificial systems: a review of the current knowledge and proposals for multi-disciplinary research , 2019, Cogn. Comput. Syst..

[37]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .

[38]  F. Binkofski,et al.  Varieties of abstract concepts: development, use and representation in the brain , 2018, Philosophical Transactions of the Royal Society B: Biological Sciences.

[39]  L. Pessoa.  Do Intelligent Robots Need Emotion? , 2017, Trends in Cognitive Sciences.

[40]  James L. McClelland,et al.  Developing the knowledge of number digits in a child-like robot , 2019, Nature Machine Intelligence.

[41]  Angelo Cangelosi,et al.  Making fingers and words count in a cognitive robot , 2013, Front. Behav. Neurosci..

[42]  Angelo Cangelosi,et al.  Robotic Services Acceptance in Smart Environments With Older Adults: User Satisfaction and Acceptability Study , 2018, Journal of medical Internet research.