Towards Intelligent Social Robots: Social Cognitive Systems in Smart Environments

We propose an institutional robotics approach to the design of socially-aware multi-robot systems, where cooperation among the robots and their social interactions with humans are guided using institutions. Inspired by the concepts stemming from economical sciences, robot institutions serve as coordination artifacts, which specify behavioral rules that are acceptable or desirable given the situation and which can be replaced by other rules to enforce new acceptable or desirable behaviors without changing the robot’s core code. In this paper we propose a formal methodology for consistent design of coordinated multi-robot behaviors intended for use in humanpopulated environments. We illustrate theoretical concepts with practical examples. Graph-based formations serve as a basis for coordinated multi-robot behaviors and concepts from the literature on human-aware navigation provide social rules that are enforced by the institutions. Experiments are carried out in a high-fidelity robotic simulator to illustrate the application of the theoretical concepts.

[1]  Stefan Wermter,et al.  Multi-modal integration of dynamic audiovisual patterns for an interactive reinforcement learning scenario , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Alberto Sanfeliu,et al.  Cooperative social robots to accompany groups of people , 2012, Int. J. Robotics Res..

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Jerome Feldman,et al.  Embodied language, best-fit analysis, and formal compositionality. , 2010, Physics of life reviews.

[5]  Yarden Katz,et al.  Pellet: A practical OWL-DL reasoner , 2007, J. Web Semant..

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

[7]  Alan C. Schultz,et al.  Heterogeneity in the Coevolved Behaviors of Mobile Robots: The Emergence of Specialists , 2001, IJCAI.

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

[9]  Sven Wachsmuth,et al.  Perception of artificial agents and utterance friendliness in dialogue , 2015, HRI 2015.

[10]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[11]  Jake K. Aggarwal,et al.  Robot-centric Activity Recognition from First-Person RGB-D Videos , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[12]  Pedro U. Lima,et al.  Formalization, Implementation, and Modeling of Institutional Controllers for Distributed Robotic Systems , 2014, Artificial Life.

[13]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[14]  Yi Guo,et al.  Distributed multi-robot evacuation incorporating human behavior , 2013, 2013 10th IEEE International Conference on Control and Automation (ICCA).

[15]  Alessandro Saffiotti,et al.  Too cool for school - adding social constraints in human aware planning , 2014 .

[16]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[17]  Agostino Poggi,et al.  Multiagent Systems , 2006, Intelligenza Artificiale.

[18]  Michael Beetz,et al.  ORO, a knowledge management platform for cognitive architectures in robotics , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Roger K. Moore,et al.  From Talking and Listening Robots to Intelligent Communicative Machines , 2014 .

[20]  Rachid Alami,et al.  Which one? Grounding the referent based on efficient human-robot interaction , 2010, 19th International Symposium in Robot and Human Interactive Communication.

[21]  Shuichi Nishio,et al.  Cloud networked robotics , 2012, IEEE Network.

[22]  Pedro U. Lima,et al.  An experimental study in wireless connectivity maintenance using up to 40 robots coordinated by an institutional robotics approach , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  E. Ostrom.  Understanding Institutional Diversity , 2005 .

[24]  E. G. Furubotn,et al.  Institutions and Economic Theory: The Contribution of the New Institutional Economics , 2005 .

[25]  Giulio Sandini,et al.  The iCub humanoid robot: An open-systems platform for research in cognitive development , 2010, Neural Networks.

[26]  Dana Kulic,et al.  Measurement Instruments for the Anthropomorphism, Animacy, Likeability, Perceived Intelligence, and Perceived Safety of Robots , 2009, Int. J. Soc. Robotics.

[27]  Gwenn Englebienne,et al.  Accurate activity recognition in a home setting , 2008, UbiComp.

[28]  Stefan Wermter,et al.  NICO — Neuro-inspired companion: A developmental humanoid robot platform for multimodal interaction , 2017, 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[29]  Joelle Pineau,et al.  Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus , 2017, Dialogue Discourse.

[30]  P. Piwek.  Dialogue with computers: dialogue games in action , 2017 .

[31]  Akihisa Ohya,et al.  A Multi-Robot System Architecture for Trajectory Control of Groups of People , 2005 .

[32]  Stefano Chessa,et al.  Robotic Ubiquitous Cognitive Ecology for Smart Homes , 2015, Journal of Intelligent & Robotic Systems.

[33]  Olivier Michel,et al.  Cyberbotics Ltd. Webots™: Professional Mobile Robot Simulation , 2004, ArXiv.

[34]  Claudio Bettini,et al.  COSAR: hybrid reasoning for context-aware activity recognition , 2011, Personal and Ubiquitous Computing.

[35]  Ben J. A. Kröse,et al.  Multi-user identification and efficient user approaching by fusing robot and ambient sensors , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[36]  Alois Knoll,et al.  Generating grammars for natural language understanding from knowledge about actions and objects , 2015, 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[37]  Stefan Wermter,et al.  Teaching emotion expressions to a human companion robot using deep neural architectures , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[38]  Geoffrey M. Hodgson,et al.  The Institutions , 2018, The Popular Arts.

[39]  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).

[40]  Heriberto Cuayáhuitl,et al.  SimpleDS: A Simple Deep Reinforcement Learning Dialogue System , 2016, IWSDS.

[41]  G. Brady.  Governing the Commons: The Evolution of Institutions for Collective Action , 1993 .

[42]  Pedro U. Lima,et al.  Graph-based distributed control for adaptive multi-robot patrolling through local formation transformation , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[43]  Jerome A. Feldman,et al.  Exploiting deep semantics and compositionality of natural language for Human-Robot-Interaction , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[44]  Nelson Pacheco da Rocha,et al.  Usability, accessibility and ambient-assisted living: a systematic literature review , 2013, Universal Access in the Information Society.

[45]  Stefan Wermter,et al.  Neural End-to-End Self-learning of Visuomotor Skills by Environment Interaction , 2017, ICANN.

[46]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[47]  Sergey Levine,et al.  End-to-End Training of Deep Visuomotor Policies , 2015, J. Mach. Learn. Res..

[48]  Annie S. Wu,et al.  The Current State of Normative Agent-Based Systems , 2011, J. Artif. Soc. Soc. Simul..

[49]  E. Hall,et al.  The Hidden Dimension , 1970 .

[50]  Hassane Alla,et al.  Discrete, continuous, and hybrid Petri Nets , 2004 .

[51]  Jochen J. Steil,et al.  Robots Show Us How to Teach Them: Feedback from Robots Shapes Tutoring Behavior during Action Learning , 2014, PloS one.

[52]  Frank Bomarius,et al.  An Event-Driven Approach to Activity Recognition in Ambient Assisted Living , 2009, AmI.

[53]  Paolo Dario,et al.  Design of a cloud robotic system to support senior citizens: the KuBo experience , 2017, Auton. Robots.

[54]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[55]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[56]  Stefan Wermter,et al.  Training Agents With Interactive Reinforcement Learning and Contextual Affordances , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[57]  Pedro U. Lima,et al.  A robotic platform for edutainment activities in a pediatric hospital , 2014, 2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC).

[58]  Robert Stevens.  Why use an ontology , 2013 .