The COVID-19 pandemic will have a profound and long-lasting impact on the entire scientific endeavor. Scientists already are adapting research programs to adapt changes in what is prioritized—and possible; educators changing way that next generation of researchers trained, flagship conferences many fields being cancelled, postponed, fundamentally transformed. These broad-reaching particularly impactful human-oriented domains such as human-robot interaction (HRI). Because in-person...

An instrument for remote control of the robot by wearable brain-computer interface (BCI) is proposed rehabilitating children with attention-deficit/hyperactivity disorder (ADHD). Augmented reality (AR) glasses generate flickering stimuli, and a single-channel electroencephalographic BCI detects elicited steady-state visual evoked potentials (SSVEPs). This allows benefiting from SSVEP robustness leaving available view movements. Together lack training, single channel maximizes device's...

Abstract Socially assistive robotics (SAR) is getting a lot of attention for its potential in assisting elderly users. However, robotic applications to be effective, they need satisfy the particular needs each user and well perceived. For this purpose, personalization based on user’s characteristics such as personality cognitive profile, their dynamic changes crucial factor. Moreover, most existing solutions rely availability specific technological infrastructures, generally requiring high...

Robotic psychological assessment is a novel field of research that explores social robots as psychometric tools for providing quick and reliable screening exams. In this study, we involved elderly participants to compare the prototype robotic cognitive test with traditional paper-and-pencil tool. Moreover, explored influence personality factors technology acceptance on testing. Results demonstrate validity conducted under professional supervision. Additionally, results show positive Openness...

Research and development in socially assistive robotics have produced several novel applications the care of senior people. However, some are still unexplored such as their use psychometric tools allowing for a quick dependable evaluation human users’ intellectual capacity. To fully exploit application social robot tool, it is necessary to account factors that might influence interaction with user cognitive performance. this end, we invited participants prototype robot-led test analyzed...

Background The Unified Theory of Acceptance and Use Technology is a self-rated questionnaire to assess twelve constructs related the level acceptance robot, consisting 41 items rated on 5-point Likert scale. aim study was conduct preliminary evaluation psychometric properties Italian version UTAUT (I-UTAUT) in sample healthy subjects (HCs). Materials methods 30 HCs underwent I-UTAUT its comprehensibility. Reliability divergent validity were evaluated 121 HCs, who also Montreal Cognitive...

Human safety and effective human-robot communication are main concerns in HRI applications. In order to achieve such goals, a system should be very robust, allowing little chance for misunderstanding the user's commands. Moreover, permit natural interaction reducing time effort needed tasks. The purpose of this work is develop general framework flexible multimodal communication. proposed architecture easy modify expand, adding or modifying input channels changing fusion strategies. paper, we...

To date, there is a wide availability of academic and commercial ICT proposals to improve urban mobility. Nevertheless, in the literature, still lack suitable solutions for door-to-door routing supporting users from their origins destinations including suggestion on where park. On other hand, an Internet-of-Things (IoT) scenario, lot novel information sources could be exploited compute more efficient mobility proposed user. As example, parking data easily collected provide multimodal routes...

Abstract In socially assistive robotics, human activity recognition plays a central role when the adaptation of robot behavior to one is required. this paper, we present an approach for activities daily living based on deep learning and skeleton data. literature, ad hoc features extraction/selection algorithms with supervised classification methods have been deployed, reaching excellent performance. Here, propose approach, combining CNN LSTM, that exploits both spatial dependencies...

Abstract Theory of Mind is crucial to understand and predict others’ behaviour, underpinning the ability engage in complex social interactions. Many studies have evaluated a robot’s attribute thoughts, beliefs, emotions humans during interactions, but few investigated human attribution robots with such capabilities. This study contributes this direction by evaluating how cognitive emotional capabilities attributed robot may be influenced some behavioural characteristics interaction. For...

This paper presents a POMDP-based dialogue system for multimodal human-robot interaction (HRI). Our aim is to exploit dialogical paradigm allow natural and robust between the human robot. The proposed should improve robustness flexibility of overall interactive system, including fusion, interpretation, decision-making. represented as Partially Observable Markov Decision Process (POMDPs) cast inherent communication ambiguity noise into model. POMDPs have been used in spoken systems, mainly...

Abstract Emotions represent a key aspect of human life and behavior. In recent years, automatic recognition emotions has become an important component in the fields affective computing human-machine interaction. Among many physiological kinematic signals that could be used to recognize emotions, acquiring facial expression images is one most natural inexpensive approaches. The creation generalized, inter-subject, model for emotion from still challenge, due anatomical, cultural environmental...

The high request for autonomous human–robot interaction (HRI), combined with the potential of machine learning (ML) techniques, allow us to deploy ML mechanisms in robot control. However, use can make robots' behavior unclear observer during phase. Recently, transparency HRI has been investigated such interactions more comprehensible. In this work, we propose a model improve reinforcement (RL) tasks scenarios: supports by having show nonverbal emotional-behavioral cues. Our considered human...

Task recognition and future human activity prediction are of importance for a safe profitable human-robot cooperation. In real scenarios, the robot has to extract this information merging knowledge task with contextual from sensors, minimizing possible misunderstandings. paper, we focus on tasks that can be represented as sequence manipulated objects performed actions. The is modelled Dynamic Bayesian Network (DBN), which takes input Objects actions separately classified starting RGB-D raw...