A Two-Layered Approach to Adaptive Dialogues for Robotic Assistance

Socially assistive robots should provide users with personalized assistance within a wide range of scenarios such as hospitals, home or social settings and private houses. Different people may have different needs both at the cognitive/physical support level and in relation to the preferences of interaction. Consequently the typology of tasks and the way the assistance is delivered can change according to the person with whom the robot is interacting. The authors’ long-term research goal is the realization of an advanced cognitive system able to support multiple assistive scenarios with adaptations over time. We here show how the integration of model-based and model-free AI technologies can contextualize robot assistive behaviors and dynamically decide what to do (assistive plan) and how to do it (assistive plan execution), according to the different features and needs of assisted persons. Although the approach is general, the paper specifically focuses on the synthesis of personalized therapies for (cognitive) stimulation of users.

[1]  Filip Karlo Dosilovic,et al.  Explainable artificial intelligence: A survey , 2018, 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[2]  Pat Langley,et al.  Cognitive architectures: Research issues and challenges , 2009, Cognitive Systems Research.

[3]  Amedeo Cesta,et al.  A Holistic Approach to Behavior Adaptation for Socially Assistive Robots , 2020, Int. J. Soc. Robotics.

[4]  C. Nass,et al.  Does computer-synthesized speech manifest personality? Experimental tests of recognition, similarity-attraction, and consistency-attraction. , 2001, Journal of experimental psychology. Applied.

[5]  David Vernon,et al.  The role of cognitive architectures in general artificial intelligence , 2018, Cognitive Systems Research.

[6]  Alex Mihailidis,et al.  Learning and Personalizing Socially Assistive Robot Behaviors to Aid with Activities of Daily Living , 2018, ACM Transactions on Human-Robot Interaction.

[7]  N. Guarino,et al.  Formal Ontology in Information Systems : Proceedings of the First International Conference(FOIS'98), June 6-8, Trento, Italy , 1998 .

[8]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[9]  Amedeo Cesta,et al.  Toward intelligent continuous assistance , 2020, J. Ambient Intell. Humaniz. Comput..

[10]  Marta Cialdea Mayer,et al.  Planning and execution with flexible timelines: a formal account , 2016, Acta Informatica.

[11]  Alessandro Saffiotti,et al.  Towards a science of integrated AI and Robotics , 2017, Artif. Intell..

[12]  Joelle Pineau,et al.  The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach , 2018, J. Artif. Intell. Res..

[13]  Amedeo Cesta,et al.  Training for crisis decision making - An approach based on plan adaptation , 2014, Knowl. Based Syst..

[14]  Amedeo Cesta,et al.  PLATINUm: A New Framework for Planning and Acting , 2017, AI*IA.

[15]  Yuandong Tian,et al.  Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees , 2018, ICLR.

[16]  Silvia Rossi,et al.  User profiling and behavioral adaptation for HRI: A survey , 2017, Pattern Recognit. Lett..

[17]  D Feil-Seifer,et al.  Socially Assistive Robotics , 2011, IEEE Robotics & Automation Magazine.

[18]  D. Feil-Seifer,et al.  Defining socially assistive robotics , 2005, 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005..

[19]  Moritz Tenorth,et al.  Representations for robot knowledge in the KnowRob framework , 2017, Artif. Intell..

[20]  Dieter Fensel,et al.  Knowledge Engineering: Principles and Methods , 1998, Data Knowl. Eng..

[21]  Sergey Levine,et al.  SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning , 2018, ICML.

[22]  Brian Scassellati,et al.  Socially assistive robotics [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[23]  John K. Tsotsos,et al.  40 years of cognitive architectures: core cognitive abilities and practical applications , 2018, Artificial Intelligence Review.

[24]  Malik Ghallab,et al.  Deliberation for autonomous robots: A survey , 2017, Artif. Intell..

[25]  Adriana Tapus,et al.  User—robot personality matching and assistive robot behavior adaptation for post-stroke rehabilitation therapy , 2008, Intell. Serv. Robotics.