Robots that maintain equilibrium: Proactivity by reasoning about user intentions and preferences

Abstract Robots need to exhibit proactive behavior if they are to be accepted in human-centered environments. A proactive robot must reason about the actions it can perform, the state of the environment, the state and the intentions of its users, and what the users deem desirable. This paper proposes a computational framework for proactive robot behavior that formalizes the above ingredients. The framework is grounded on the notion of Equilibrium Maintenance: current and future states are continuously evaluated to identify opportunities for acting that steer the system into more desirable states. We show that this process leads a robot to proactively generate its own goals and enact them, and that the obtained behavior depends on a model of user intentions, preferences, and the temporal horizon used in prediction. A number of examples show that our framework accounts for even slight variations in user preference models and perceived user intentions. We also show how the level of informedness of the system is easily customizable.

[1]  Régis Sabbadin,et al.  Possibilistic Markov decision processes , 2001 .

[2]  Alessandro Saffiotti,et al.  Proactivity through equilibrium maintenance with fuzzy desirability , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[3]  Anand S. Rao,et al.  Modeling Rational Agents within a BDI-Architecture , 1997, KR.

[4]  Michael T. Cox Perpetual Self-Aware Cognitive Agents , 2007, AI Mag..

[5]  Alessandro Saffiotti,et al.  Inferring robot goals from violations of semantic knowledge , 2013, Robotics Auton. Syst..

[6]  Michael Beetz,et al.  AI Reasoning Methods for Robotics , 2016, Springer Handbook of Robotics, 2nd Ed..

[7]  M. Tomasello,et al.  Understanding and sharing intentions: The origins of cultural cognition , 2005, Behavioral and Brain Sciences.

[8]  Henriette Cramer,et al.  The effects of robot touch and proactive behaviour on perceptions of human-robot interactions , 2009, 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[9]  Pierre-Yves Oudeyer,et al.  What is Intrinsic Motivation? A Typology of Computational Approaches , 2007, Frontiers Neurorobotics.

[10]  Amit Kumar Pandey,et al.  Socially Intelligent Robots, the Next Generation of Consumer Robots and the Challenges , 2016, ICT Innovations.

[11]  Nick Hawes,et al.  A survey of motivation frameworks for intelligent systems , 2011, Artif. Intell..

[12]  Anand S. Rao,et al.  An architecture for real-time reasoning and system control , 1992, IEEE Expert.

[13]  J. Baldwin,et al.  Dynamic programming for fuzzy systems with fuzzy environment , 1982 .

[14]  David W. Aha,et al.  Goal-Driven Autonomy in a Navy Strategy Simulation , 2010, AAAI.

[15]  Alessandro Saffiotti,et al.  Intention Reconsideration in Theory and Practice , 2000, ECAI.

[16]  Matthew Klenk,et al.  Breadth of Approaches to Goal Reasoning: A Research Survey , 2013 .

[17]  Mica R. Endsley,et al.  Toward a Theory of Situation Awareness in Dynamic Systems , 1995, Hum. Factors.

[18]  M. Tomasello,et al.  Altruistic Helping in Human Infants and Young Chimpanzees , 2006, Science.

[19]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[20]  Cengiz Kahraman,et al.  Fuzzy Multicriteria Decision-Making: A Literature Review , 2015, Int. J. Comput. Intell. Syst..

[21]  Yu Zhang,et al.  A human factors analysis of proactive support in human-robot teaming , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[23]  Eyke Hllermeier,et al.  Preference Learning , 2010 .

[24]  Shirin Sohrabi,et al.  Plan Recognition as Planning Revisited , 2016, IJCAI.

[25]  Michael Beetz,et al.  Towards Comprehensive Computational Models for Plan-Based Control of Autonomous Robots , 2005, Mechanizing Mathematical Reasoning.

[26]  Hector Muñoz-Avila,et al.  MIDCA: A Metacognitive, Integrated Dual-Cycle Architecture for Self-Regulated Autonomy , 2016, AAAI.

[27]  Adam M. Grant,et al.  The dynamics of proactivity at work , 2008 .

[28]  Georgios N. Yannakakis Preference learning for affective modeling , 2009, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops.

[29]  Hector J. Levesque,et al.  Intention is Choice with Commitment , 1990, Artif. Intell..

[30]  Martha E. Pollack,et al.  There's More to Life than Making Plans: Plan Management in Dynamic, Multiagent Environments , 1999, AI Mag..

[31]  Marc Hanheide,et al.  A Framework for Goal Generation and Management , 2010, AAAI 2010.

[32]  Alessandro Saffiotti,et al.  Making Robots Proactive through Equilibrium Maintenance , 2016, IJCAI.

[33]  Alessandro Saffiotti,et al.  A constraint-based approach for proactive, context-aware human support , 2012, J. Ambient Intell. Smart Environ..

[34]  Rachid Alami,et al.  Towards a Task-Aware Proactive Sociable Robot Based on Multi-state Perspective-Taking , 2013, Int. J. Soc. Robotics.

[35]  Michael Wooldridge,et al.  The dMARS Architecture: A Specification of the Distributed Multi-Agent Reasoning System , 2004, Autonomous Agents and Multi-Agent Systems.