Despite important progress in recent years, social robots are still far away from showing advanced behavior for interaction and adaptation in human environments. Thus, we are interested in studying social cognition in human-robot interaction (HRI), notably in improving communication skills relying on joint attention (JA) and knowledge sharing. Since JA involves low-level cognitive processes in humans, we take into account the implications of Moravec’s Paradox and focus on the aspect of knowledge representation. Inspired by 4E cognition principles, we study egocentric localization through the concept of sensory ego-sphere. We propose a neural network architecture named AEGO to model attention for each agent in interaction and show how to fuse information in a common representation space. From the perspective of dynamic fields theory, AEGO takes into account the dynamics of bottom-up and top-down modulation processes and the effects of neural excitatory and inhibitory synaptic interaction. In this work we evaluate the model in simulation and experiments with the robot Pepper in JA tasks based on proprioception, vision, rudimentary natural language and Hebbian plasticity. Results show that AEGO is convenient for HRI, allowing the human and the robot to share attention and knowledge about objects in scenarios close to everyday situations. AEGO constitutes a novel brain-inspired architecture to model attention that is suitable for multi-agent applications relying on social cognition skills, having the potential to generalize to several robotics platforms and HRI scenarios.

Developments in the field of social robotics open interesting opportunities for applications in healthcare, education, and services. For this, studying engagement in human-robot interaction (HRI) is crucial for improving the quality of interactive experiences. Questionnaires are powerful in describing voluntary behavior; however, engagement is often an implicit non-voluntary behavior that reaches awareness only once initiated. Inspired by research in cognitive psychology, we propose a behavioral feature to quantify engagement in HRI through the measurement of spontaneous movement and spectral wavelet analysis. For this, we conducted an experiment during which participants listened to sad stories narrated by a moving social robot. Throughout the experiment, we tracked the participants’ spontaneous and non-voluntary sway movements with a motion capture system. The experiments were conducted with three robotic platforms (Buddy, Pepper, and Nao). Results showed that spontaneous body sway can be modulated by social robots within no-goal-oriented interaction. This opens up the application possibility of our methodology to various modes of HRI such as collaboration.

Coexisting with others and interacting in society implies sharing knowledge and attention about world objects, events, features, episodes, and even imagination or abstract ideas in time and space. Inspired by human phenomenological, cognitive and behavioral research, this work focuses on the study of joint attention (JA) for human-robot interaction (HRI), based on two main assumptions: a) the perception and representation of attention jointness constitute an isomorphic relation, and b) inspiration on dynamic neural fields (DNF) theory is a promising way to investigate contextual and non-linear spatio-temporal relations underlying attention and knowledge sharing in HRI. Taking into account the previous considerations, we propose a topology-based model for JA named TOP-JAM, which is able to represent and track in real-time JA states, from observations of behavioral data. More importantly, the model consists in a representation that can be directly understood by human beings, which conforms to robo-ethical principles in social robotics. This study evaluates computational properties of the model in simulation. Through a real experiment with the robot Pepper, the study shows that TOP-JAM is able to track JA in a triad interaction scenario.

Embodiment and subjective experience in humanrobot interaction are important aspects to consider when studying both natural cognition and adaptive robotics to human environments. Although several researches have focused on nonverbal communication and collaboration, the study of autonomous physical interaction has obtained less attention. From the perspective of neurorobotics, we investigate the relation between intentionality, motor compliance, cognitive compliance, and behavior emergence. We propose a variational model inspired by the principles of predictive coding and active inference to study intentionality and cognitive compliance, and an intermittent control concept for motor deliberation and compliance based on torque feed-back. Our experiments with the humanoid Torobo portrait interesting perspectives for the bio-inspired study of developmental and social processes.

The research on robot tracking has focused on the problem of information fusion from redundant parametric estimations, though the aspect of choosing an adaptive fusion policy, that is computationally efficient, and is able to reduce the impact of un-modeled noise, are still open issues. The objective of this work is to study the problem of underwater robot localization. For this, we have considered a task relying on inertial and geophysical sensory. We propose an heuristic model that performs adaptable fusion of information based on the principle of contextually anticipating the localization signal within an ordered neighborhood, such that a set of nodes properties is related to the task context, and the confidence on individual estimates is evaluated before fusing information. The results obtained show that our model outperforms the Kalman filter and the Augmented Monte Carlo Localization algorithms in the task.

The study of the motivational aspect and its relevance to the comprehension of the efficacy of learning has been the subject matter of several researches. According to the Self-determination Theory (SDT) there is a relation between the context, the motivation, and the performance of individuals in a given task. Thus, a continuum is defined between intrinsic, extrinsic, and lack of motivation; so individuals intrinsically motivated would perform optimally. In order to adequate the communication module of the system Sapiens for the learning of efficient energy consumption, this work has proposed to develop an instrument to evaluate the level of situational motivation of individuals, and to design persuasive messages to increase the engagement on the task, based on the motivation profiles described by SDT. For this, a methodology was defined comprising the following stages: (i) bibliographic research of the state-of-art scales to assess motivation; (ii) design of a data collection instrument in the form of a structured questionnaire; (iii) evaluation of the instrument considering an heterogeneous sample of 589 college, high-school, technical, master, and doctoral students, aged between 14 and 80 years, at three different situations (the library, the classroom, and leisure); (iv) design of the persuasive messages to enhance the user engagement on the task. The resulting instrument was named Ubiquitous Situational Motivation Scale (USMS), consisted in 18 questions presented as a 7-points Likert Scale, that measures four motivational factors with Cronbach alpha coefficients ranging from 0.61 to 0.86. Our study revealed that subjects' motivation profile varied according to the context, so leisure activities were respectively more related to intrinsic motivation than the library and the classroom activities, and suggests that classroom activities are probably more related to external regulation. The results were also consistent with the continuum hypothesis of SDT. The evaluation with potential users showed that the persuasive messages designed based on the motivational profiles were positively rated. From these results the persuasive module will integrated to the Sapiens platform so the performance of the users can be studied.

International audience

International audience