Emotional Robot Research Articles

Learning Bodily Expression of Emotion for Social Robots Through Human Interaction

Human facial and bodily expressions play a crucial role in human–human interaction to convey the communicator’s feelings. Being echoed by the influence of human social behavior, recent studies in human–robot interaction (HRI) have investigated how to generate emotional behaviors for social robots. Emotional behaviors can enhance user engagement, allowing the user to interact with robots in a transparent manner. However, they are ambiguous and affected by many factors, such as personality traits, cultures, and environments. This article focuses on developing the robot’s emotional bodily expressions adopting the user’s affective gestures. We propose the behavior selection and transformation model, enabling the robots to incrementally learn from the user’s gestures, to select the user’s habitual behaviors, and to transform the selected behaviors into robot motions. The experimental results under several scenarios showed that the proposed incremental learning model endows a social robot with the capability of entering into a positive, long-lasting HRI. We have also confirmed that the robot can express emotions through the imitated motions of the user. The robot’s emotional gestures that reflected the interacting partner’s traits were widely accepted within the same cultural group, and perceptible across different cultural groups in different ways.

Behavior Models of Emotion-Featured Robots: A Survey

Emotions are important in many aspects of human behavior. Emotions are displayed on human faces, they are reflected in human memory, and they even influence human intelligence. The creation of robots that try to mimic humans arises the question of how the concept of emotion can be transferred to robots. There is no unique answer to the question, however many robots that leverage emotions exist. By summarizing the work done on these robots we try to enlighten the relations between robots and emotions from several perspectives. We first identify how artificial emotion can be defined in a robotic system. Next, we investigate the possible roles of emotions in robotic behavior models and analyze different implementations of the concept of emotion in these models. Finally, we elaborate on the evaluation of how emotions influence human-robot interaction. For this purpose, we qualitatively analyzed a selected set of robots that include emotions in their model. Considering the diversity of state-of-the-art approaches to using emotions in robots, we try to present the findings in a structured and comprehensive way that could be valuable for future researchers.

User Affect Elicitation with a Socially Emotional Robot

To effectively communicate with people, social robots must be capable of detecting, interpreting, and responding to human affect during human–robot interactions (HRIs). In order to accurately detect user affect during HRIs, affect elicitation techniques need to be developed to create and train appropriate affect detection models. In this paper, we present such a novel affect elicitation and detection method for social robots in HRIs. Non-verbal emotional behaviors of the social robot were designed to elicit user affect, which was directly measured through electroencephalography (EEG) signals. HRI experiments with both younger and older adults were conducted to evaluate our affect elicitation technique and compare the two types of affect detection models we developed and trained utilizing multilayer perceptron neural networks (NNs) and support vector machines (SVMs). The results showed that; on average, the self-reported valence and arousal were consistent with the intended elicited affect. Furthermore, it was also noted that the EEG data obtained could be used to train affect detection models with the NN models achieving higher classification rates

Sharing Stress With a Robot: What Would a Robot Say?

With the prevalence of mental health problems today, designing human-robot interaction for mental health intervention is not only possible, but critical. The current experiment examined how three types of robot disclosure (emotional, technical, and by-proxy) affect robot perception and human disclosure behavior during a stress-sharing activity. Emotional robot disclosure resulted in the lowest robot perceived safety. Post-hoc analysis revealed that increased perceived stress predicted reduced human disclosure, user satisfaction, robot likability, and future robot use. Negative attitudes toward robots also predicted reduced intention for future robot use. This work informs on the possible design of robot disclosure, as well as how individual attributes, such as perceived stress, can impact human robot interaction in a mental health context.

Research on the emotional cognitive evaluation model based on artificial neural network

the neural network, fuzzy set theory and evolutionary algorithm in artificial intelligence are all intelligent information processing theories that follow the biological processing mode. These theories are realized by rational logical thinking mode without considering the role of human perceptual thinking in the information processing process, such as emotion and cognition. Among them, the neural network mainly imitates the function of the mental system of human, adopts the method from the bottom to the top, and processes the difficult language pattern information through a large number of complicated connections of neurons. Artificial neural network (Ann) is a cross research field of artificial intelligence and life science. This theory mainly imitates the information processing mechanism of organisms in nature and is mainly used in intelligent information processing systems that can adapt to long-term changes in the environment. Therefore, neural network has important application significance in the research of intelligence, robot and artificial emotion.

Speech Understanding System for Emotional Companion Robots

Abstract Within the project of emotional robot F-2 we develop a natural text parser for automatic speech comprehension. It is aimed at the construction of semantic representation and the selection of “scripts” – units for inference modelling and the selection of emotional reactions for the robot. The design of the speech understanding system follows the traditional concept of linguistic levels: it consequently constructs morphological, syntactic and semantic representations. Unlike neural networks, these representations are readable for a developer, so the accumulated data is available for statistical and analytical processing. Parser accepts written text after speech recognition (during actual talks with the robot) or during processing of everyday news and blogs from the internet. Parser may save text representations on each level of linguistic model to a database. In particular, semantic representations from daily internet processing are used as an accumulated knowledge database for the robot. In this paper we discuss the approach to the model of understanding through a competition of scripts on a robot companion.

Non-verbal behavior of the robot companion: a contribution to the likeability

Abstract Modern emotional robots can support multimodal communicative interaction with humans through speech, hand gestures, head movements, eye and mouth animations. In the framework of this work, the contribution of individual active organs of the robot to the overall positive impression created by the robot in the user is investigated. The F-2 robot was used as an experimental platform. The experimental study revealed that users are significantly more likely to prefer a robot that uses gestures, head movements, eyes and mouth animation in its behavior compared to a robot in which the corresponding part of the body is stationary. The impact of robot’s eye movements on the user is not so clear: subjects significantly more often prefer a robot that uses eye movements in behavior, but they relatively rarely notice the difference between the two patterns of robot behavior – the behavior of the robot with fixed eyes and behavior of one with moving eyes.

On the Possibility of Emotional Robots

In this article, I examine whether the possibility exists that in the foreseeable future, robot technology will permit the development of emotional robots. As the title suggests, the content is of a technological as well as of a philosophical nature. As a matter of fact, my aim in writing this paper was that of bridging two distinctive fields in a world where humanity has become accustomed to technological innovations while overlooking any consequential complications arising from such inventions. To this end, I review and commentate on what Anders Sandberg, Paul Thagard, Nikhil Churamani and other thinkers have contributed on the subject matter. The literature review indicates that in the short to the medium term, scientists will only design and engineers will only build robots that will be able to only learn, be trained, or under the most optimistic conditions only simulate human emotions. However, in the long term the possibility exists for technology to advance to such a state so as to permit an entire human brain to be emulated in a robot via a concept named ‘mind uploading’. If one day that becomes a reality, that will be the point where humanity will possibly come closest to creating robots with emotions.

An emotional model for swarm robotics

Swarm robotics is a system of multiple robots where a desired collective behavior emerges from the interactions between the robots and with the environment. This paper proposes an emotional model for the robots, to allow emerging behaviors. The emotional model uses four universal emotions: anger, disgust, sadness, and joy, assigned to each robot based on the level of satisfaction of its basic needs. These emotions lie on a spectrum where depending where the emotion of the robot lies, can affect its behavior and of its neighboring robots. The more negative the emotion is, the more individualistic it becomes in its decisions. The more positive the robot is in its emotion, the more it will consider the group and global goals. Each robot is able to recognize another robot's emotion in the system based on their current state, using the AR2P recognition algorithm. Specifically, the paper addresses emotions’ influence on the behavior of the system, at the individual and collective levels, and the emotions’ effects on the emergent behaviors of the multi-robot system. The paper analyses two emergent scenarios: nectar harvesting and object transportation, and shows the importance of the emotions into the emergent behavior in a multi-robot system

Intelligent architectures for robotics: The merging of cognition and emotion.

What is the place of emotion in intelligent robots? In the past two decades, researchers have advocated for the inclusion of some emotion-related components in the general information processing architecture of autonomous agents, say, for better communication with humans, or to instill a sense of urgency to action. The framework advanced here goes beyond these approaches and proposes that emotion and motivation need to be integrated with all aspects of the architecture. Thus, cognitive-emotional integration is a key design principle. Emotion is not an "add on" that endows a robot with "feelings" (for instance, reporting or expressing its internal state). It allows the significance of percepts, plans, and actions to be an integral part of all its computations. It is hypothesized that a sophisticated artificial intelligence cannot be built from separate cognitive and emotional modules. A hypothetical test inspired by the Turing test, called the Dolores test, is proposed to test this assertion.

REAL-TIME CLASSIFICATION OF FACIAL EXPRESSIONS USING A PRINCIPAL COMPONENT ANALYSIS AND CONVOLUTIONAL NEURAL NETWORK

Classification of facial expressions has become an essential part of computer systems and human-computer fast interaction. It is employed in various applications such as digital entertainment, customer service, driver monitoring, and emotional robots. Moreover, it has been studied through several aspects related to the face itself when facial expressions change based on the point of view or perspective. Facial curves such as eyebrows, nose, lips, and mouth will automatically change. Most of the proposed methods have limited frontal Face Expressions Recognition (FER), and their performance decrease when handling non-frontal and multi-view FER cases. This study combined both methods in the classification of facial expressions, namely the Principal Component Analysis (PCA) and Convolutional Neural Network (CNN) methods. The results of this study proved to be more accurate than that of previous studies. The combination of PCA and CNN methods in the Static Facial Expressions in The Wild (SFEW) 2.0 dataset obtained an accuracy amounting to 70.4%; the CNN method alone only obtained an accuracy amounting to 60.9%.

Emotions in Robots: Embodied Interaction in Social and Non-Social Environments

Whether they are considered discrete or dimensional, emotions are ’embodied’ phenomena [...]

Modeling and Evaluating Emotion, Contextual Head Movement and Voices for a Social Robot Storyteller

Storytelling bears great potential as prospective application for social robots. Through their embodiment and potential for multi-modal behavior, they can enhance current storytelling media, for example books or audio books. We combined theoretical knowledge about designing storytelling robots with an analysis of human storytellers to implement the behavior of a robot storyteller. We tested the following modalities in three perception studies: emotional behavior, contextual head movements, and voice acting through different synthetic voices. Our results suggest, that an emotional robot storyteller is able to transport participants equally well as the traditional audio book, contextual head movement has to be carefully modeled to be recognized, and voice acting can improve narrative presence and can make the robot more interesting. With the present contribution, we provide guidance for modeling and evaluating the behavior of a social robot storyteller, and suggest that the careful integration of emotional display and different voices can enhance the perception of a robot storytelling experience.

Impact of an Emotional Robot on Quality of Working Life of Caregivers in a Geriatric Unit

Impact of an Emotional Robot on Quality of Working Life of Caregivers in a Geriatric Unit

Robot’s adaptive emotional feedback sustains children’s social engagement and promotes their vocabulary learning: a long-term child–robot interaction study

In this article, we present an emotion and memory model for a social robot. The model allowed the robot to create a memory account of a child’s emotional events over four individual sessions. The robot then adapted its behaviour based on the developed memory. The model was applied on the NAO robot to teach vocabulary to children while playing the popular game ‘Snakes and Ladders’. We conducted an exploratory evaluation of our model with 24 children at a primary school for 2 weeks to verify its impact on children’s long-term social engagement and overall vocabulary learning. Our preliminary results showed that the behaviour generated based on our model was able to sustain social engagement. In addition, it also helped children to improve their vocabulary. We also evaluated the impact of the positive, negative and neutral emotional feedback of the NAO robot on children’s vocabulary learning. Three groups of children (eight per group) interacted with the robot on four separate occasions over a period of 2 weeks. Our results showed that the condition where the robot displayed positive emotional feedback had a significantly positive effect on the child’s vocabulary learning performance as compared to the two other conditions: negative feedback and neutral feedback.

The Mechanics of Fear. Re-envisioning Anxiety through Emerging Technologies of Affect/Funktionsweisen der Furcht. Neue Konzepte von Angst im Kontext der emotionalen Robotik

While there has been ample research in the fields of psychology and human- robot interaction on humans’ fear toward robots, advancements in artificial emotional intelligence and emotional robotics suggest the need to investigate not only the mechanisms by which humans in different social contexts de- velop anxiety toward robots but also the mechanics by which robots might develop anxiety themselves. Based on a year of ethnographic research among engineers in Japan modeling emotion in robots, this article contends that exploring how robots are both designed and imagined to sense anxiety reveals productive feedback loops between entertainment robotics, artificial intelligence research, and an evolving psychology of human-robot relations in Japan. By outlining some of the social, scientific, and political implications of these feedback loops, the essay aims to help answer the question of how recent technological strategies to realize robots that not only read, perform, but also in a philosophical and social sense have emotion are reshaping the designs of psychological research on fear and anxiety in contemporary Japan.

Social robots: The influence of human and robot characteristics on acceptance

Abstract Research in social robotics is focused on the development of robots that can provide physical and cognitive support in a socially interactive way. Whilst some studies have previously investigated the importance of user characteristics (age, gender, education, robot familiarity, mood) in the acceptance of social robots as well as the influence a robot’s displayed emotion (positive, negative, neutral) has on the interaction, these two aspects are rarely combined. Therefore, this study attempts to highlight the need to consider the influence that both human and robot attributes can have on social robot acceptance. Eighty-six participants completed implicit and explicit measures of mood before viewing one of three video clips containing a positive, negative or neutral social robot (Pepper) followed by questionnaires on robot acceptance and perception. Gender and education were not associated with acceptance; however, several constructs of the acceptance questionnaire significantly correlated with age and mood. For example, those younger and those experiencing sadness or loneliness were more dependent on the opinions of others (as measured by the social influence construct of the acceptance questionnaire). This highlights the importance of mood in the introduction of social robots into vulnerable populations. Robot familiarity also correlated with robot acceptance with those more familiar finding the robot less useful and less enjoyable, this is important as robots become more prominent in society. Displayed robot emotion significantly influenced acceptance and perception with the positive robot appearing more childlike than the negative and neutral robot, and the neutral robot the least helpful. These findings emphasise the importance of both user and robot characteristics in the successful integration of social robots.

Information-Driven Multirobot Behavior Adaptation to Emotional Intention in Human–Robot Interaction

To adapt robots’ behavior to human emotional intention, an information-driven multirobot behavior adaptation mechanism is proposed in human–robot interaction (HRI). In the mechanism, optimal policy of behavior is selected by information-driven fuzzy friend- ${Q}$ learning (IDFFQ), and facial expression with identification information are used to understand human emotional intention. It aims to make robots be capable of understanding and adapting their behaviors to human emotional intention, in such a way that HRI runs smoothly. Simulation experiments are performed according to a scenario of drinking at a bar. Results show that the proposed IDFFQ reduces 51 learning steps compared to the fuzzy production rule-based friend- ${Q}$ learning (FPRFQ), and computational time is about 1/4 of the time consumed in FPRFQ. In Addition, the accuracy of emotion recognition and emotional intention understanding are 80.36% and 85.71%, respectively. The preliminary application experiments are carried out to the developing emotional social robot system, and the basic experimental results are shown in the scenario of drinking at a bar with three emotional robots and 12 volunteers.

A new emotional robot assistant that facilitates human interaction and persuasion

The development of robots that are truly sociable requires understanding how human interactions can be applied to the interaction between humans and robots. A sociable robot must be able to interact with people taking into account aspects like verbal and non-verbal communications (emotions, postures, gestures). This work presents a social robot which main goal is to provide assistance to older people in carrying out their daily activities (through suggestions or reminders). In addition, the robot presents non-verbal communications like perceiving emotions and displaying human identifiable emotions in order to express empathy. A prototype of the robot is being tested in a daycare center in the northern area of Portugal.

Opportunistic inference and emotion in service robots

Opportunistic inference and emotion in service robots