Robot in the Mirror: Toward an Embodied Computational Model of Mirror Self-Recognition

Self-recognition or self-awareness is a capacity attributed typically only to humans and few other species. The definitions of these concepts vary and little is known about the mechanisms behind them. However, there is a Turing test-like benchmark: the mirror self-recognition, which consists in covertly putting a mark on the face of the tested subject, placing her in front of a mirror, and observing the reactions. In this work, first, we provide a mechanistic decomposition, or process model, of what components are required to pass this test. Based on these, we provide suggestions for empirical research. In particular, in our view, the way the infants or animals reach for the mark should be studied in detail. Second, we develop a model to enable the humanoid robot Nao to pass the test. The core of our technical contribution is learning the appearance representation and visual novelty detection by means of learning the generative model of the face with deep auto-encoders and exploiting the prediction error. The mark is identified as a salient region on the face and reaching action is triggered, relying on a previously learned mapping to arm joint angles. The architecture is tested on two robots with completely different face.

[1]  P. Haggard,et al.  Having a body versus moving your body: Neural signatures of agency and body-ownership , 2010, Neuropsychologia.

[2]  Yasuo Kuniyoshi,et al.  Contingency Perception and Agency Measure in Visuo-Motor Spiking Neural Networks , 2009, IEEE Transactions on Autonomous Mental Development.

[3]  Karl J. Friston,et al.  Action and behavior: a free-energy formulation , 2010, Biological Cybernetics.

[4]  Margot J. Taylor,et al.  Face processing stages: Impact of difficulty and the separation of effects , 2006, Brain Research.

[5]  J. Piaget The construction of reality in the child , 1954 .

[6]  Tarek R. Besold,et al.  A match does not make a sense: on the sufficiency of the comparator model for explaining the sense of agency , 2019, Neuroscience of consciousness.

[7]  A. Young,et al.  Understanding face recognition. , 1986, British journal of psychology.

[8]  Pablo Lanillos,et al.  A deep active inference model of the rubber-hand illusion , 2020, ArXiv.

[9]  A. Cangelosi,et al.  Developmental Robotics: From Babies to Robots , 2015 .

[10]  Rajesh P. N. Rao,et al.  Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. , 1999 .

[11]  Rolf Pfeifer,et al.  Robots as Powerful Allies for the Study of Embodied Cognition from the Bottom Up , 2018, The Oxford Handbook of 4E Cognition.

[12]  Gordon Cheng,et al.  An Empirical Study of Active Inference on a Humanoid Robot , 2021, IEEE Transactions on Cognitive and Developmental Systems.

[13]  Markus F. Neumann,et al.  Repetition effects in human ERPs to faces , 2016, Cortex.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  M. Tsakiris,et al.  The free-energy self: A predictive coding account of self-recognition , 2014, Neuroscience & Biobehavioral Reviews.

[16]  Gordon Cheng,et al.  Multisensory object discovery via self-detection and artificial attention , 2016, 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[17]  G. G. Gallop Chimpanzees: self-recognition. , 1970, Science.

[18]  Ole Jensen,et al.  The ‘Narcissus Effect’: Top-down alpha-beta band modulation of face-related brain areas during self-face processing , 2020, NeuroImage.

[19]  Selmer Bringsjord,et al.  Real robots that pass human tests of self-consciousness , 2015, 2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[20]  Daniela Corbetta,et al.  Mapping the feel of the arm with the sight of the object: on the embodied origins of infant reaching , 2014, Front. Psychol..

[21]  G. Gallup Chimpanzees: Self-Recognition , 1970, Science.

[22]  Giorgio Metta,et al.  Towards manipulation-driven vision , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  M. Corbetta,et al.  Control of goal-directed and stimulus-driven attention in the brain , 2002, Nature Reviews Neuroscience.

[24]  Tony J. Prescott,et al.  The Synthetic Psychology of the Self , 2018, Intelligent Systems, Control and Automation: Science and Engineering.

[25]  M. Eimer The Face-Sensitive N170 Component of the Event-Related Brain Potential , 2011 .

[26]  G. G. Gallup,et al.  Self‐awareness and the emergence of mind in primates , 1982, American journal of primatology.

[27]  Brian Scassellati,et al.  Using probabilistic reasoning over time to self-recognize , 2009, Robotics Auton. Syst..

[28]  Masaki Ogino,et al.  Body Image Constructed from Motor and Tactile Images with Visual Information , 2007, Int. J. Humanoid Robotics.

[29]  X. Gu,et al.  Self as Object: Emerging Trends in Self Research , 2017, Trends in Neurosciences.

[30]  F. D. Waal Are We Smart Enough to Know How Smart Animals Are , 2016 .

[31]  Philippe Gaussier,et al.  Visual Learning for Reaching and Body-Schema with Gain-Field Networks , 2018, 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[32]  F. D. de Waal Fish, mirrors, and a gradualist perspective on self-awareness , 2019, PLoS biology.

[33]  R. W. Mitchell,et al.  Mental models of mirror-self-recognition: Two theories , 1993 .

[34]  Gordon Cheng,et al.  Robot self/other distinction: active inference meets neural networks learning in a mirror , 2020, ECAI.

[35]  Justin W. Hart Robot Self-Modeling , 2014 .

[36]  J. Haxby,et al.  Neural systems for recognition of familiar faces , 2007, Neuropsychologia.

[37]  Mu-ming Poo,et al.  Mirror-Induced Self-Directed Behaviors in Rhesus Monkeys after Visual-Somatosensory Training , 2015, Current Biology.

[38]  Gordon G. Gallup,et al.  Mirror self-recognition: a review and critique of attempts to promote and engineer self-recognition in primates , 2015, Primates.

[39]  M. Hoffman IMITATION IN CHILDREN , 2007 .

[40]  A. Engel,et al.  Tactile remapping: from coordinate transformation to integration in sensorimotor processing , 2015, Trends in Cognitive Sciences.

[41]  Gordon Cheng,et al.  Enactive self: A study of engineering perspectives to obtain the sensorimotor self through enaction , 2017, 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[42]  Alejandro Hernández Arieta,et al.  Body Schema in Robotics: A Review , 2010, IEEE Transactions on Autonomous Mental Development.

[43]  Giulio Sandini,et al.  Sensorimotor coordination in a "baby" robot: learning about objects through grasping. , 2007, Progress in brain research.

[44]  U. Neisser Five kinds of self‐knowledge , 1988 .

[45]  Gordon Cheng,et al.  Yielding Self-Perception in Robots Through Sensorimotor Contingencies , 2017, IEEE Transactions on Cognitive and Developmental Systems.

[46]  Pontus Loviken,et al.  Prerequisites for an Artificial Self , 2020, Frontiers in Neurorobotics.

[47]  Luc Steels,et al.  The robot in the mirror , 2008, Connect. Sci..

[48]  Gordon Cheng,et al.  Active inference body perception and action for humanoid robots , 2019, ArXiv.

[49]  J. Anderson,et al.  The development of self-recognition: a review. , 1984, Developmental psychobiology.

[50]  Bernhard Hommel,et al.  Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation , 2017, Journal of visualized experiments : JoVE.

[51]  Gordon Cheng,et al.  Sensorimotor learning for artificial body perception , 2018, IROS 2018.

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

[53]  Yasuo Kuniyoshi,et al.  Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period , 2019, Philosophical Transactions of the Royal Society B.

[54]  Karl J. Friston The free-energy principle: a unified brain theory? , 2010, Nature Reviews Neuroscience.

[55]  Dana H. Ballard,et al.  Modular Learning in Neural Networks , 1987, AAAI.

[56]  Kim A. Bard,et al.  Self‐Awareness in Human and Chimpanzee Infants: What Is Measured and What Is Meant by the Mark and Mirror Test? , 2006 .

[57]  A. Bigelow,et al.  The correspondence between self- and image movement as a cue to self-recognition for young children. , 1981, The Journal of genetic psychology.

[58]  Minoru Asada,et al.  Is it my body? Body extraction from uninterpreted sensory data based on the invariance of multiple sensory attributes , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[59]  Jun Tani,et al.  An Interpretation of the "Self" From the Dynamical Systems Perspective: A Constructivist Approach , 1998 .

[60]  S. Gallagher Philosophical conceptions of the self: implications for cognitive science , 2000, Trends in Cognitive Sciences.

[61]  Verena V. Hafner,et al.  Self-supervised Body Image Acquisition Using a Deep Neural Network for Sensorimotor Prediction , 2019, 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[62]  A. Capilla,et al.  Is your own face more than a highly familiar face? , 2019, Biological Psychology.

[63]  B. Amsterdam,et al.  Mirror self-image reactions before age two. , 1972, Developmental psychobiology.

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