The Impact of Representing Time and Intention

policies from time-dependent POMDP models or by policies from two less expressive model variants performed this interaction in a driving simulator with human drivers. The time-dependentPOMDP policies achievedbetter results than those of the models without explicit time representation or human intention as hidden state, both according to the reward obtained and to people’s subjective impressions of how socially appropriate and natural the robot’s behavior was. These results demonstrate both the relative superiority of these representation choices and the effectiveness of this approach to planning for socially situated tasks.

[1]  Lik Mui,et al.  Notions of reputation in multi-agents systems: a review , 2002, AAMAS '02.

[2]  Trey Smith,et al.  Probabilistic planning for robotic exploration , 2007 .

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

[4]  Henrik Walter,et al.  Understanding Intentions in Social Interaction: The Role of the Anterior Paracingulate Cortex , 2004, Journal of Cognitive Neuroscience.

[5]  Frank Broz,et al.  Planning for human-robot interaction: representing time and human intention , 2008 .

[6]  Panos E. Trahanias,et al.  Probabilistic Autonomous Robot Navigation in Dynamic Environments with Human Motion Prediction , 2010, Int. J. Soc. Robotics.

[7]  H. Bekkering,et al.  Joint action: bodies and minds moving together , 2006, Trends in Cognitive Sciences.

[8]  R. Aumann.  Agreeing to disagree. , 1976, Nature cell biology.

[9]  Uta Frith,et al.  The Biological Basis of Social Interaction , 2001 .

[10]  Reid G. Simmons,et al.  Heuristic Search Value Iteration for POMDPs , 2004, UAI.

[11]  Xinwei Deng,et al.  Experimental design , 2012, WIREs Data Mining Knowl. Discov..

[12]  Alessandro Saffiotti,et al.  A Human-Aware Robot Task Planner , 2009, ICAPS.

[13]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[14]  A. Colman.  Cooperation, psychological game theory, and limitations of rationality in social interaction , 2003, Behavioral and Brain Sciences.

[15]  John Maynard Smith,et al.  The origin of altruism , 1998, Nature.

[16]  A. Meltzoff.  Understanding the Intentions of Others: Re-Enactment of Intended Acts by 18-Month-Old Children. , 1995, Developmental psychology.

[17]  Mitsuo Kawato,et al.  Activation of the Human Superior Temporal Gyrus during Observation of Goal Attribution by Intentional Objects , 2004, Journal of Cognitive Neuroscience.

[18]  Cynthia Breazeal,et al.  Crowdsourcing Real World Human-Robot Dialog and Teamwork through Online Multiplayer Games , 2011, AI Mag..

[19]  Kevin A. Pelphrey,et al.  Grasping the Intentions of Others: The Perceived Intentionality of an Action Influences Activity in the Superior Temporal Sulcus during Social Perception , 2004, Journal of Cognitive Neuroscience.

[20]  Michael E. Bratman,et al.  What is intention , 1987 .

[21]  Joelle Pineau,et al.  Point-based value iteration: An anytime algorithm for POMDPs , 2003, IJCAI.

[22]  Illah R. Nourbakhsh,et al.  DERVISH - An Office-Navigating Robot , 1995, AI Mag..

[23]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[24]  Craig Boutilier,et al.  VDCBPI: an Approximate Scalable Algorithm for Large POMDPs , 2004, NIPS.

[25]  Louis ten Bosch,et al.  Durational Aspects of Turn-Taking in Spontaneous Face-to-Face and Telephone Dialogues , 2004, TSD.

[26]  Christos Dimitrakakis,et al.  TORCS, The Open Racing Car Simulator, v1.3.5 , 2013 .

[27]  Karl-Martin Ehrhart,et al.  Social information processing in strategic decision-making: Why timing matters , 2001 .

[28]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[29]  Jeff G. Schneider,et al.  Approximate solutions for partially observable stochastic games with common payoffs , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[30]  Illah R. Nourbakhsh,et al.  Planning for Human-Robot Interaction Using Time-State Aggregated POMDPs , 2008, AAAI.

[31]  Kai Oliver Arras,et al.  Planning Problems for Social Robots , 2011, ICAPS.

[32]  Daniel Stahl,et al.  Sensitivity to interpersonal timing at 3 and 6 months of age , 2006 .

[33]  Illah R. Nourbakhsh,et al.  Designing POMDP models of socially situated tasks , 2011, 2011 RO-MAN.

[34]  Reid G. Simmons,et al.  Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic , 2006, AAAI.

[35]  Jodie A. Baird,et al.  Discerning intentions in dynamic human action , 2001, Trends in Cognitive Sciences.