COM2009-3009_L14_Cognitive-Systems.pdf

© 2023 The University of Sheffield COM2009-3009 Robotics Lecture 14 Cognitive Systems https://youtu.be/ErgfgF0uwUo COM2009-3009 Robotics: Lecture 14 slide 1 1 © 2023 The University of Sheffield COM2009-3009 Robotics Lecture 14 Cognitive Systems COM2009-3009 Robotics: Lecture 14 slide 2 2 1...

© 2023 The University of Sheffield COM2009-3009 Robotics Lecture 14 Cognitive Systems https://youtu.be/ErgfgF0uwUo COM2009-3009 Robotics: Lecture 14 slide 1 1 © 2023 The University of Sheffield COM2009-3009 Robotics Lecture 14 Cognitive Systems COM2009-3009 Robotics: Lecture 14 slide 2 2 1 © 2023 The University of Sheffield Deliberative vs. Reactive Control (from Lecture 2) Arkin, R. C. (1998). Behavior-Based Robotics. Cambridge, MA: The MIT Press. COM2009-3009 Robotics: Lecture 14 slide 3 3 © 2023 The University of Sheffield Cognition Definition: – derived from “getting” (co) “to know” (gnoscere) – the mental act or process by which knowledge is acquired (including perception, intuition and reasoning) – the knowledge that results from such an act or process Collins English Dictionary. (2009). William Collins Sons & Co. Ltd. COM2009-3009 Robotics: Lecture 14 slide 4 4 2 © 2023 The University of Sheffield Cognitive Systems COM2009-3009 Robotics: Lecture 14 slide 5 5 © 2023 The University of Sheffield Cognitive Robotics https://youtu.be/5kBiBe0wZDw “Cognitive Robotics focuses on designing and building robots that have the ability to learn from experience and from others, commit relevant knowledge and skills to memory, retrieve them as the context requires, and flexibly use this knowledge to select appropriate actions in the pursuit of their goals, while anticipating the outcome of those actions when doing so.” Dr Alessandra Sciutti Sandini et al. (2023), Encyclopedia of Robotics. COM2009-3009 Robotics: Lecture 14 slide 6 6 3 © 2023 The University of Sheffield Cognitive Paradigms GOFAI • ‘Cognitivist’ – – – – – – computational symbolic rational encapsulated structured algorithmic ‘System 2’ New AI • ‘Emergent’ – – – – – – connectionist dynamical enactive self-organizing situated embodied ‘System 1’ COM2009-3009 Robotics: Lecture 14 slide 7 7 © 2023 The University of Sheffield “Thinking Fast and Slow” ‘System 1’ – – – – – – fast automatic frequent emotional stereotypic unconscious ‘System 2’ – – – – – – slow effortful infrequent logical calculating conscious Kahneman, D. (2011). Thinking, Fast and Slow. Penguin Books. COM2009-3009 Robotics: Lecture 14 slide 8 8 4 © 2023 The University of Sheffield Cognitive Architecture: ACT-R Anderson, J. R., Bothell, D., Byrne, M. D., Douglass, S., Lebiere, C., & Qin, Y . (2004). An integrated theory of the mind. Psychological Review, 1036–1060. Adaptive Control of Thought - Rational COM2009-3009 Robotics: Lecture 14 slide 9 9 © 2023 The University of Sheffield Cognitive Architecture: ACT-R https://youtu.be/zolWEO8PRQg COM2009-3009 Robotics: Lecture 14 slide 10 10 5 © 2023 The University of Sheffield Cognitive Architecture: SOAR Laird, J. E. (2012). The SOAR Cognitive Architecture, The MIT Press. State, Operator And Result COM2009-3009 Robotics: Lecture 14 slide 11 11 © 2023 The University of Sheffield Cognitive Architecture: SOAR https://youtu.be/GX5N_U3-lco COM2009-3009 Robotics: Lecture 14 slide 12 12 6 © 2023 The University of Sheffield Global Workspace Theory • The brain can best be understood as a ‘theatre’ • Consciousness acts as a ‘bright spot’ on the stage (directed there by the spotlight of attention) • The ‘stage’ corresponds to working memory Baars, B. J. (1988), A Cognitive Theory of Consciousness, Cambridge University Press COM2009-3009 Robotics: Lecture 14 slide 13 13 © 2023 The University of Sheffield Global Workspace Theory NRM model Webots simulator Motor Cortex Camera input Salience populations Khepera Association Cortex Camera view Reward & punishment Motor veto Motor output Global Workspace https://slideplayer.com/slide/793881/ COM2009-3009 Robotics: Lecture 14 slide 14 14 7 © 2023 The University of Sheffield Action Selection • Autonomy implies autonomous decision making • Decision making implies a reward function • A reward function implies a ‘motivation’ • Two competing views … – extrinsic motivation – intrinsic motivation COM2009-3009 Robotics: Lecture 14 slide 15 15 © 2023 The University of Sheffield Extrinsic Motivation EXTERNAL ENVIRONMENT rewards actions Reward comes from outside the agent Action Selection sensations AUTONOMOUS AGENT Oudeyer, P.-Y., & Kaplan, F. (2007). What is intrinsic motivation? A typology of computational approaches. Frontiers in Neurorobotics, 1, 6. COM2009-3009 Robotics: Lecture 14 slide 16 16 8 © 2023 The University of Sheffield Intrinsic Motivation EXTERNAL ENVIRONMENT Motivation System rewards actions Reward comes from inside the agent sensations Action Selection AUTONOMOUS AGENT Oudeyer, P.-Y., & Kaplan, F. (2007). What is intrinsic motivation? A typology of computational approaches. Frontiers in Neurorobotics, 1, 6. COM2009-3009 Robotics: Lecture 14 slide 17 17 © 2023 The University of Sheffield Maslow’s ‘Hierarchy of Needs’ Maslow, A. H. (1943). A theory of human motivation. Psychological Review, 50, 370396. WiFi COM2009-3009 Robotics: Lecture 14 slide 18 18 9 © 2023 The University of Sheffield Consequences of ‘Motivation’ • An individual’s behaviour is conditioned on a set of basic needs and goals = comparitor Does this sound familiar? • ‘Appraisal mechanisms’ assess any given situation with regard to an individual’s needs and goals • The outcome of such an appraisal process is ‘emotion’ • Emotion drives action (to meet needs) = error • Emotion is ‘felt’ but may also be ‘expressed’ • Some aspects of emotion are hypothesised to be ‘universal’ Scherer, K. R., Schorr, A., & Johnstone, T. (Eds.). (2001). Appraisal Processes in Emotion: Theory, Methods, Research. New York and Oxford: Oxford University Press. COM2009-3009 Robotics: Lecture 14 slide 19 19 © 2023 The University of Sheffield Expressive Emotion in Animals Darwin, C. (2009). The Expression of the Emotions in Man and Animals. London: Harper Perennial. COM2009-3009 Robotics: Lecture 14 slide 20 20 10 © 2023 The University of Sheffield Expressive Emotion in Humans Darwin, C. (2009). The Expression of the Emotions in Man and Animals. London: Harper Perennial. COM2009-3009 Robotics: Lecture 14 slide 21 21 © 2023 The University of Sheffield Expressive Emotion in Robots COM2009-3009 Robotics: Lecture 14 slide 22 22 11 © 2023 The University of Sheffield Basic Emotions COM2009-3009 Robotics: Lecture 14 slide 23 23 © 2023 The University of Sheffield The ‘Discrete’ Theory of Emotion • Hypothesises a small number of basic emotions: – – – – – – happiness sadness fear anger surprise disgust • Supposed to be specific physiological response patterns to external stimuli Ekman, P. (1999). Basic emotions. In T. Dalgleish & M. Power (Eds.), Handbook of Cognition and Emotion (pp. 301-320). New York: John Wiley. COM2009-3009 Robotics: Lecture 14 slide 24 24 12 © 2023 The University of Sheffield The ‘Dimensional’ Approach Mehrabian, A. (1996). Pleasurearousaldominance: A general framework for describing and measuring individual differences in temperament. Current Psychology: Developmental, Learning, Personality, Social, 14, 261292. • ‘Valence’ (pleasure) – positive emotion (e.g. success in achieving a goal) – negative emotion (e.g. failure to achieve a goal) • ‘Arousal’ – intensity of emotional experience • ‘Dominance’ ‘PAD’ model – control versus lack of control COM2009-3009 Robotics: Lecture 14 slide 25 25 © 2023 The University of Sheffield The ‘Dimensional’ Approach Maps a wide variety of emotions into a low-dimensional space … Arousal “angry” Wundt W (1874). Grundzüge der Physiologischen Psychologie, Engelmann, Leipzig. Valence active “happy” negative positive “sad” “content” passive COM2009-3009 Robotics: Lecture 14 slide 26 26 13 © 2023 The University of Sheffield Annotation Tool: FEELTRACE Cowie, R., DouglasCowie, E., Savvidou, S., McMahon, E., Sawey, M., & Schröder, M. (2000). FEELTRACE: an instrument for recording perceived emotion in real time, ISCA Workshop on Speech and Emotion (pp. 19-24). COM2009-3009 Robotics: Lecture 14 slide 27 27 © 2023 The University of Sheffield Cognitive Appraisal Theory Smith, C. A., & Lazarus, R. (1990). Emotion and adaptation. In L. A. Pervin (Ed.), Handbook of Personality: theory and research (pp. 609-637). New York: Guildford Press. COM2009-3009 Robotics: Lecture 14 slide 28 28 14 © 2023 The University of Sheffield Cognitive Appraisal Theory Klaus Scherer Scherer, K. R., Schorr, A., & Johnstone, T. (Eds.). (2001). Appraisal Processes in Emotion: Theory, Methods, Research. New York and Oxford: Oxford University Press. COM2009-3009 Robotics: Lecture 14 slide 29 29 © 2023 The University of Sheffield Computational Appraisal Model • Appraisal variables: – desirability does this event help/hurt my goals? Gratch, J., & Marcella, S. (2007). Computational models of emotion, Affective Computing and Intelligent Interaction (ACII). Paris. – likelihood how likely that the event will occur? – unexpectedness was the event expected? – causal attribution who deserves blame? – coping potential am I able to deal with the event? • Emotional consequences – undesirable + uncertain ® ‘fear’ – desirable + certain ® ‘joy’ – undesirable + caused-by-other ® ‘anger’ (at other) COM2009-3009 Robotics: Lecture 14 slide 30 30 15 © 2023 The University of Sheffield The OCC* Model * Ortony, A., Clore, G., & Collins, A. (1988). The Cognitive Structure of Emotions. Cambridge University Press. Steunebrink, B. R., Dastani, M., & Meyer, J.J. C. (2009). The OCC model revisited. 4th Workshop on Emotion and Computing. COM2009-3009 Robotics: Lecture 14 slide 31 31 © 2023 The University of Sheffield Computational Model of Emotion Drives = ‘homeostatic variables’ Gratch, J., & Marcella, S. (2007). Computational models of emotion, Affective Computing and Intelligent Interaction (ACII). Paris. Maximum (warmth, energy, etc.) error Optimum level reference Current level Deficit Þ Action (to reduce deficit) observation Lethal boundary COM2009-3009 Robotics: Lecture 14 slide 32 32 16 © 2023 The University of Sheffield Computational Model of Emotion Emotion (valence) Appraisal Motivation/ Effort (arousal) Kp Motor Command Action Intention Perception Consequence (as seen in Lectures 5 & 6) COM2009-3009 Robotics: Lecture 14 slide 33 33 © 2023 The University of Sheffield Needs-Driven ‘MBDIAC’ Agent Moore, R. K., & Nicolao, M. (2017). Towards a Needs-Based Architecture for ‘Intelligent’ Communicative Agents: Speaking with Intention. Frontiers in Robotics and AI, 4(66). Mutual Beliefs Desires Intentions Actions & Consequences COM2009-3009 Robotics: Lecture 14 slide 34 34 17 © 2023 The University of Sheffield Distributed Adaptive Control (DAC) The ‘H4W’ problem … • • • • • How (to survive) Why (the motivation for action in terms of needs, drives and goals) What (the objects in the world that actions pertain to) Where (the location of objects in the world and the self) When (the timing of action relative to the dynamics of the world) Forebrain Brainstem Spinal Cord Verschure, P. F. M. J. (2012). Distributed adaptive control: A theory of the mind, brain, body nexus. Biologically Inspired Cognitive Architectures, 1, 55-72. Periphery COM2009-3009 Robotics: Lecture 14 slide 35 35 © 2023 The University of Sheffield Collins, E. C., Prescott, T. J., Mitchinson, B., & Conran, S. (2015). MIRO: a versatile biomimetic edutainment robot. In Proceedings of the 12th International Conference on Advances in Computer Entertainment Technology - ACE ’15 (pp. 1–4). Iskandar, Malaysia: ACM Press. COM2009-3009 Robotics: Lecture 14 MiRo slide 36 36 18 © 2023 The University of Sheffield Collins, E. C., Prescott, T. J., Mitchinson, B., & Conran, S. (2015). MIRO: a versatile biomimetic edutainment robot. In Proceedings of the 12th International Conference on Advances in Computer Entertainment Technology - ACE ’15 (pp. 1–4). Iskandar, Malaysia: ACM Press. COM2009-3009 Robotics: Lecture 14 MiRo slide 37 37 © 2023 The University of Sheffield Moore, R. K., & Mitchinson, B. (2017). A biomimetic vocalisation system for MiRo. In M. Mangan, M. Cutkosky, A. Mura, P. F. M. J. Verschure, T. Prescott, & N. Lepora (Eds.), Living Machines 2017, LNAI 10384 (pp. 363–374). Stanford, CA: Springer International Publishing. COM2009-3009 Robotics: Lecture 14 slide 38 38 19 © 2023 The University of Sheffield This lecture has covered … • • • • • • • • • • • Cognition Cognitive architectures Behaviour Extrinsic/intrinsic motivation Maslow’s ‘hierarchy of needs’ Theories of emotion Cognitive appraisal theory The OCC model Computational model of emotion Distributed adaptive control MiRo COM2009-3009 Robotics: Lecture 14 slide 39 39 © 2023 The University of Sheffield Any Questions ? (or you can post on the ‘Lecture’ Discussion Forum) COM2009-3009 Robotics: Lecture 14 slide 40 40 20 © 2023 The University of Sheffield Next time … Interactive Systems COM2009-3009 Robotics: Lecture 14 slide 41 41 21