This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS 1 Toward a Context-Aware Human–Robot Interaction Framework Based on Cognitive Development Jo ˜ ao Quintas , Gonçalo S. Martins, Luis Santos, Paulo Menezes, and Jorge Dias Abstract—The purpose of this paper was to understand how an agent’s performance is affected when interaction workflows are incorporated in its information model and decision-making process. Our expectation was that this incorporation could reduce errors and faults on agent’s operation, improving its interaction performance. We based this expectation on the existing chal- lenges in designing and implementing artificial social agents, where an approach based on predefined user scenarios and action scripts is insufficient to account for uncertainty in perception or unclear expectations from the user. Therefore, we developed a framework that captures the expected behavior of the agent into descriptive scenarios and then translated these into the agent’s information model and used the resulting representation in prob- abilistic planning and decision making to control interaction. Our results indicated an improvement in terms of specificity while maintaining precision and recall, suggesting that the hypoth- esis being proposed in our approach is plausible. We believe the presented framework will contribute to the field of cognitive robotics, e.g., by improving the usability of artificial social com- panions, thus overcoming the limitations imposed by approaches that use predefined static models for an agent’s behavior resulting in non-natural interaction. Index Terms—Active assisted living, adaptive systems, cloud robotics, context awareness, decision systems, human–machine systems, interaction design. I. I NTRODUCTION I N OUR recent works [1]–[5], we designed and imple- mented two different approaches of artificial social com- panions (ASCs). Both approaches aimed to operate as assistive technology in real-world indoor environments. Their primary mission was to help older adults in managing activities of their daily life and staying connected with their social circle. Manuscript received November 12, 2017; revised February 14, 2018; accepted April 30, 2018. This work was supported by the GrowMeUp Project through the European Commission within the H2020-PHC-2014 under Grant 643647. This paper was recommended by Associate Editor A. Hussain. (Corresponding author: Jo ˜ ao Quintas.) J. Quintas is with the Laboratory for Automation and Systems, Instituto Pedro Nunes, 3030-199 Coimbra, Portugal, and also with the Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, 3000-214 Coimbra, Portugal (e-mail: jquintas@ipn.pt). G. S. Martins, L. Santos, and P. Menezes are with the Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, 3000-214 Coimbra, Portugal (e-mail: gmartins@isr.uc.pt; luis@isr.uc.pt; pm@deec.uc.pt). J. Dias is with the Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, 3000-214 Coimbra, Portugal, and also with the Robotics Institute, Khalifa University, Abu Dhabi 127788, UAE (e-mail: jorge@deec.uc.pt). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TSMC.2018.2833384 Fig. 1. CaMeLi and GrowMeUp systems being tested by older adults. In CaMeLi, 1 we designed and implemented a virtual part- ner capable of showing a variety of dialogues and a wide spectrum of animated facial expressions while providing a set of services to answer the user’s needs/requests. Moreover, in GrowMeUp, 2 we designed and implemented a service robotic system able to learn an older person’s needs and habits over time and enhance (grow up/scale up) its functionality to com- pensate for the degradation of their abilities and to support, encourage, and engage the older persons to stay active, inde- pendent and socially involved while carrying out their daily lives at home. In both systems, we implemented various degrees of human interaction and autonomy that aimed to per- form cognitive-like functions and accomplish real-time goals in terms of interaction and self-sufficiency. In other words, the user and agent could interact through multiple modalities, which included speech commands, gestures, touch screen, or other modes. In both cases, we dedicated most of our efforts to developing perception capabilities, user interfaces, and the 1 http://www.cameli.eu/ 2 http://www.growmeup.eu/ 2168-2216 c  2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.