Robots Thinking Fast and Slow: On Dual Process Theory and Metacognition in Embodied AI

Recent progress in AI technology has been breathtaking. However, many of the advances have played to the strengths of virtual environments: infinite training data is available, risk-free exploration is possible, acting is essentially free. In contrast, we require our robots to robustly operate in real-time, to learn from a limited amount of data, take missionand sometimes safety-critical decisions and increasingly even display a knack for creative problem solving. To bridge this gap, here we offer an alternative view of recent advances in AI. In particular, we posit that, for the first time, roboticists can draw meaningful functional parallels between AI technology and components identified in the cognitive sciences as pivotal to robust operation in the real world: Dual Process Theory and metacognition. Revisiting recent work in robot learning, we establish the building blocks of a Dual Process Theory for robots and highlight potentially fruitful future research directions towards delivering robust, versatile and safe embodied AI.

[1]  Jiajun Wu,et al.  Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning , 2015, NIPS.

[2]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[3]  L. Reder,et al.  What determines initial feeling of knowing? Familiarity with question terms, not with the answer , 1992 .

[4]  Charles Richter,et al.  Safe Visual Navigation via Deep Learning and Novelty Detection , 2017, Robotics: Science and Systems.

[5]  Rudolph Triebel,et al.  Introspective classification for robot perception , 2016, Int. J. Robotics Res..

[6]  Andrea Vedaldi,et al.  ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking , 2018, ECCV.

[7]  Tor Lattimore,et al.  Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning , 2017, NIPS.

[8]  Thomas J. Walsh,et al.  Knows what it knows: a framework for self-aware learning , 2008, ICML '08.

[9]  Jeannette Bohg,et al.  Leveraging big data for grasp planning , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Winston Churchill,et al.  Off the beaten track: Predicting localisation performance in visual teach and repeat , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Yee Whye Teh,et al.  Continual Unsupervised Representation Learning , 2019, NeurIPS.

[12]  Michael T. Cox.  Metacognition in computation: A selected research review , 2005, Artif. Intell..

[13]  Christoph H. Lampert,et al.  A PAC-Bayesian bound for Lifelong Learning , 2013, ICML.

[14]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[15]  Abhinav Gupta,et al.  Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Jakub W. Pachocki,et al.  Learning dexterous in-hand manipulation , 2018, Int. J. Robotics Res..

[17]  David Barber,et al.  Thinking Fast and Slow with Deep Learning and Tree Search , 2017, NIPS.

[18]  Jiajun Wu,et al.  Learning to See Physics via Visual De-animation , 2017, NIPS.

[19]  Mario Fritz,et al.  Visual stability prediction for robotic manipulation , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Jane X. Wang,et al.  Reinforcement Learning, Fast and Slow , 2019, Trends in Cognitive Sciences.

[21]  Martial Hebert,et al.  Introspective perception: Learning to predict failures in vision systems , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[23]  Daniel J. Hsu.  Algorithms for active learning , 2010 .

[24]  Ingmar Posner,et al.  Fit for Purpose? Predicting Perception Performance Based on Past Experience , 2016, ISER.

[25]  Ingmar Posner,et al.  Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[26]  Stefan Schaal,et al.  Skill learning and task outcome prediction for manipulation , 2011, 2011 IEEE International Conference on Robotics and Automation.

[27]  Ophelia Deroy,et al.  Metacognition in Multisensory Perception , 2016, Trends in Cognitive Sciences.

[28]  Sergey Levine,et al.  Reasoning About Physical Interactions with Object-Oriented Prediction and Planning , 2018, ICLR.

[29]  Jürgen Leitner,et al.  Learning robust, real-time, reactive robotic grasping , 2019, Int. J. Robotics Res..

[30]  Danica Kragic,et al.  Analytic grasp success prediction with tactile feedback , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[31]  N. McGlynn.  Thinking fast and slow. , 2014, Australian veterinary journal.