Handbook of Research on Synthetic Emotions and Sociable Robotics: New Applications in Affective Computing and Artificial Intelligence
Abstract
Decades of scientific research on neurophysiology have proven emotions are not simply a minor aspect of human activity, but rather a fundamental one. The Handbook of Research on Synthetic Emotions and Sociable Robotics: New Applications in Affective Computing and Artificial Intelligence focuses on the integration of emotions into artificial environments such as computers and robotics. Written by an international collaboration of experts within the field, this Handbook of Research covers topics such as emotion simulation and emotion synthetic development.
... At the same time, gestures used are either very simplified, such as directional movements , circles or Arabic numbers, or very different [8, 19] from each other, which, to some extent, simplifies the recognition process. Applications based on gesture recognition have been presented in [12]. Relatively little research effort has been given to acceleration based gesture user identification , however. ...
... Compared to simple Euclidean (Fig. 2left) distance measure the DTW (Fig. 2right) method has the ability to warp time axis and thus allows for optimal alignment between the two time series. Because gestures acquired with accelerometer sensors equipped devices can be typically described as multidimensional time series, the proposed method is very well suited for our purposes, as is also evident from related work [10, 12, 14, 17, 25]. Given two time series X=(x 1 ,x 2 ,…,x i ,…,x IXI ) and Y=(y 1 ,y 2 ,…,y j ,…,y IYI ) of lengths IXI and IYI where x i , y j ∈ℜ, a cost matrix D with dimensions IXI by IYI is constructed. ...
We present an intuitive, implicit, gesture based identification system suited for applications such as the user login to home multimedia services, with less strict security requirements. The term "implicit gesture" in this work refers to a natural physical hand manipulation of the control device performed by the user, who picks it up from its neutral motionless position or shakes it. For reference with other related systems, explicit and well defined identification gestures were used. Gestures were acquired by an accelerometer sensor equipped device in a form of the Nintendo WiiMote remote controller. A dynamic time warping method is used at the core of our gesture based identification system. To significantly increase the computational efficiency and temporal stability, the "super-gesture" concept was intro-duced, where acceleration features of multiple gestures are combined in only one super-gesture template per each user. User evaluation spanning over a period of 10 days and including 10 participants was conducted. User evaluation study results show that our algorithm ensures nearly 100 % recognition accuracy when using explicit identification signature gestures and between 88 % and 77 % recognition accuracy when the system needs to distinguish between 5 and 10 users, using the implicit "pick-up" gesture. Performance of the proposed system is comparable to the results of other related works when using explicit identification gestures, while showing that implicit gesture based identification is also possible and viable.
... Through previous research on emotional modelling [12][13][14] we have contributed to the design of a multimodal model for the use of emotional affordances in HRI [15,16]. Most of HRI literature that includes emotional affordances is biased by two important aspects: first, it maintains an over-simplistic ...
The concept of affordance perception is one of the distinctive traits of human cognition; and its application to robots can dramatically improve the quality of human-robot interaction (HRI). In this paper we explore and discuss the idea of "emotional affordances" by proposing a viable model for implementation into HRI; which considers allocentric and multimodal perception. We consider "2-ways" affordances: perceived object triggering an emotion; and perceived human emotion expression triggering an action. In order to make the implementation generic; the proposed model includes a library that can be customised depending on the specific robot and application scenario. We present the AAA (Affordance-Appraisal-Arousal) model; which incorporates Plutchik's Wheel of Emotions; and we outline some numerical examples of how it can be used in different scenarios.
... Through previous research on emotional modelling [12][13][14] we have contributed to the design of a multimodal model for the use of emotional affordances in HRI [15,16]. Most of HRI literature that includes emotional affordances is biased by two important aspects: first, it maintains an over-simplistic ...
Affordances are an important concept in cognition, which can be applied to robots in order to perform a successful human-robot interaction (HRI). In this paper we explore and discuss the idea of emotional affordances and propose a viable model for implementation into HRI. We consider “2-ways” affordances: perceived object triggering an emotion, and perceived human emotion expression triggering an action. In order to make the implementation generic, the proposed model includes a library that can be customised depending on the specific robot and application’s scenario. We present the AAA (Affordance-Appraisal-Arousal) model, which incorporates Plutchik’s Wheel of Emotions, and show some examples of simulation and possible scenarios.
... Emotion, as a necessary cognitive variable, is something necessary for AI, despite all the possible debates about qualia (Megill 2014). Analyses of the most recent approaches to machines and emotions have been undertaken and looked at vast amounts of existing literature on emotions and machines (Vallverdú and Casacuberta 2009;Vallverdú 2012Vallverdú , 2014). Researchers can easily distinguish between three main areas of research: (a) affective computing (Picard 1997), (b) social robotics (Breazeal 2002) and (c) emotional modelling (Sloman (1982Sloman ( , 1997Sloman ( , 2002); 7 Hudlicka 2011). ...
The next evolution of intelligent, physical life on earth will be to artificial, super-intelligent agents or even entities we might call ‘post’- or ‘trans’ humans. And, contrary to popular opinion about the man-made advanced intelligences, these entities will not be just information-driven machines devoid of emotion. Instead, today’s computing and Artificial Intelligence (AI) science has set us on the path that we fully anticipate a technological Singularity event. From this event we expect the emergence of intelligent, living entities that have the capacity to integrate massive amounts of data, but this computing will be controlled by emotional mechanisms. These new forms of life will live side-by-side with humanity so the real, foreseeable problem of this post-Singularity, post-cognitive era will be an existential one—and a possible misalignment between us (humans) and ‘them’ (the new entities). The different forms of life will pursue different goals, likely to be mediated by different, or even opposite, emotional syntaxes. How humans will interact with these new post-cognitive, emotional Singularity Entities has yet to be defined, but new social patterns will surely emerge.
... Affective computing aims at developing systems capable of recognizing, analyzing, and even emulating human emotional states [23]. It is an offshoot of computer science, cognitive science, linguistics, and psychology with a number of applications in robotics [31] [30], social media analysis [19], online marketing [8], and political campaigns [18]. Tensors are n-dimensional arrays generalizing the one-and two-dimensional arrays, namely vectors and matrices [4] [12]. ...
For large directed graphs ranking vertices is an algorithmic as well as a computational challenge. Also it is a cornerstone problem in fields so diverse such as online social media, combinatorial optimization, deep learning, econometrics, and computational neuroscience. Gell-point centrality metric is a common case of structural vertex ranking which can be efficiently computed through power method. This paper proposes harmonic centrality, also a structural ranking which can be computed equally efficiently. When the graph represents a network, both methods are oblivious to its functionality. To address that issue, a tensor based methodology is proposed for combining functional characteristics with these structural metrics. As a concrete demonstration, the tensor fusion methodology was implemented in Java over Neo4j and Tensor toolbox and was applied to a Twitter subgraph. The functional features were directly related to affective computing, while the hashtags in this subgraph were relared to a current controversial political topic, namely #brexit.
... My aim is not to make a clumsy and aggressive critic to AmI but to clarify some important points that could help to improve its research and correct implementation. From my expertise in Philosophy of Computer Sciences, Computational Epistemology, Artificial Emotions and HRI [9][10][11][12][13][14][15][16][17][18][19][20], I have a broad perspective on how interacts nature, technology and cognition (natural as well as artificial) and I consider that there are some important points that must be understood by researchers in order to create better AmI. At the same time, the idea of 'Ambient Stupidity' must be understood within the framework of recent cognitive theories, such as bounded rationality, or situated cognition. ...
AmI is clearly the next step into the evolution of the integration in daily life of computer technologies and AI products. Despite of the revolutionary nature of AmI, its analysis and media attention was big in the middle of 21st century decade, but decreasing since then. And this is a mistake, because the new social tendencies as well as the advancements in technological equipment and data procession techniques are allowing a next step into the advancement of AmI. Some general mistakes have been pointed and labeled as 'Ambient stupidity' and a broad philosophical analysis framework is suggested in order to prepare and improve the advent of Big AmI. At the same time, some critical remarks on the nature of human cognitive processes are introduced or reviewed. Finally, the request of new tools to deal with multivariate and dynamic sources of data is showed as a necessity of future researches.
We have examined the attitude and moral perception of 228 college students (63 Japanese and 165 non-Japanese) towards artificial intelligence (AI) in an international university in Japan. The students were asked to select a single most significant ethical issue associated with AI in the future from a list of nine ethical issues suggested by the World Economic Forum, and to explain why they believed that their chosen issues were most important. The majority of students (n = 149, 65%) chose unemployment as the major ethical issue related to AI. The second largest group of students (n = 29, 13%) were concerned with ethical issues related to emotional AI, including the impact of AI on human behavior and emotion. The paper discusses the results in detail and concludes that, while policymakers must consider how to ameliorate the impact of AI on employment, AI engineers need to consider the emotional aspects of AI in research and development, as well.
English Follows
Depuis leur apparition au milieu du XXe siècle dans le domaine industriel, les robots se développent dans de nombreux secteurs économiques, autour de l’utilisation de l’intelligence artificielle (IA).
Dans cette communication, après avoir examiné ce que signifie aujourd’hui la notion de robot, nous analysons les questions éthiques qu’engendre la robotique dans divers secteurs de la société, à commencer par l’industrie, en passant par la robotique militaire et policière, la santé, l’éducation, les robots ménagers et en terminant par l’agriculture et l’environnement.
À partir de cette analyse, nous recherchons un cadre éthique pour la robotique, dont nous essayons de définir une problématique à partir du couple « action et responsabilité » des robots.
Towards an ethic of robotics
Since their appearance in the middle of the twentieth century in the industrial field, robots are developing in many economic sectors, around the use of artificial intelligence (AI).
In this paper, after examining what the concept of robot means today, we analyze the ethical issues that robotics engenders in various sectors of society, starting with industry, through military and police robotics, health, education, household robots and ending with agriculture and the environment.
From this analysis, we seek an ethical framework for robotics, which we try to define a problematic from the couple “action and responsibility” of robots.
Affective Computing is a rapidly growing field spurred by advancements in artificial intelligence, but often, held back by the inability to translate psychological theories of emotion into tractable computational models. To address this, we propose a probabilistic programming approach to affective computing, which models psychological-grounded theories as generative models of emotion, and implements them as stochastic, executable computer programs. We first review probabilistic approaches that integrate reasoning about emotions with reasoning about other latent mental states (e.g., beliefs, desires) in context. Recently-developed probabilistic programming languages offer several key desidarata over previous approaches, such as: (i) flexibility in representing emotions and emotional processes; (ii) modularity and compositionality; (iii) integration with deep learning libraries that facilitate efficient inference and learning from large, naturalistic data; and (iv) ease of adoption. Furthermore, using a probabilistic programming framework allows a standardized platform for theory-building and experimentation: Competing theories (e.g., of appraisal or other emotional processes) can be easily compared via modular substitution of code followed by model comparison. To jumpstart adoption, we illustrate our points with executable code that researchers can easily modify for their own models. We end with a discussion of applications and future directions of the probabilistic programming approach
Creativity and diversity are key components of success in idea generation, but each includes many dimensions. Paradigm-relatedness is an indicator of the style of creativity and diversity that has been overlooked often in assessing ideation. The goals for this study were to synthesize the literature on paradigm-relatedness, and develop and test alternative approaches for operationalizing paradigm-relatedness in ideation. The synthesis of the literature focused on reviewing both paradigm-relatedness theoretical frameworks and methodological approaches. Then, two alternative paradigm-relatedness metric approaches—category-based and component-based—were developed. Finally, ideation data was collected and coded to evaluate the reliability, ease of use, and potential applications of each approach. The category-based approach was a more reliable and faster way to code paradigm-relatedness, and so it may be more suited for research or evaluation at scale. In contrast, the component-based approach provided more explicit information on all aspects of paradigm-relatedness, but was more challenging to code reliably and more time-consuming. The component-based approach may be more suited to guiding smaller teams or individual designers in achieving paradigm-relatedness creativity and diversity. Neither approach was found to be universally ideal, and so consideration of the trade-offs is important in deciding which is most appropriate in a given situation.
In this paper, we look at a specific issue with practical Turing tests, namely the right of the machine to remain silent during interrogation. In particular, we consider the possibility of a machine passing the Turing test simply by not saying anything. We include a number of transcripts from practical Turing tests in which silence has actually occurred on the part of a hidden entity. Each of the transcripts considered here resulted in a judge being unable to make the ‘right identification’, i.e., they could not say for certain which hidden entity was the machine.
The opinion mining and human-agent interaction communities are currently addressing sentiment analysis from different perspectives that comprise, on the one hand, disparate sentiment-related phenomena and computational representations, and on the other hand, different detection and dialog management methods. In this paper we identify and discuss the growing opportunities for cross-disciplinary work that may increase individual advances. Sentiment/opinion detection methods used in human-agent interaction are indeed rare and, when they are employed, they are not different from the ones used in opinion mining and consequently not designed for socio-affective interactions (timing constraint of the interaction, sentiment analysis as an input and an output of interaction strategies). To support our claims, we present a comparative state of the art which analyzes the sentiment-related phenomena and the sentiment detection methods used in both communities and makes an overview of the goals of socio-affective human-agent strategies. We propose then different possibilities for mutual benefit, specifying several research tracks and discussing the open questions and prospects. To show the feasibility of the general guidelines proposed we also approach them from a specific perspective by applying them to the case of the Greta embodied conversational agents platform and discuss the way they can be used to make a more significative sentiment analysis for human-agent interactions in two different use cases: job interviews and dialogs with museum visitors.
Humans perform acts and imitate other humans' actions by innate mechanisms that imply the unconscious notion of innerbodiment. In this chapter, the author suggests a mechanistic method to capture, discretize and understand human actions, following a semi-supervised WOZ system that could allow robotic learning by imitation or even self-learning. A syntax and semantics basic model of human actions guide is provided as well as a philosophical analysis of the notion of action.
It has been recognized that human behavior is an observable consequence of the interactions between cognitive and affective functions. This perception has motivated the study of human emotions in disciplines such as psychology and neuroscience and led to the formulation of a number of theories and models that attempt to explain the mechanisms underlying this human process. In the field of artificial intelligence, these theoretical findings have posed a series of challenges in the development of autonomous agents (AAs) capable of exhibiting very believable and human-like behaviors. One of these challenges is the design and implementation of computational models of emotions (CMEs), which are software systems designed to provide AAs with proper mechanisms for the processing of emotional information, elicitation of synthetic emotions, and generation of emotional behaviors. In this paper, we review this type of computational model from the perspective of their development. Particularly, we investigate five design aspects that influence their development process: theoretical foundations, operating cycle, interaction between cognition and emotion, architectural design, and role in cognitive agent architectures. We provide discussions about key issues and challenges in the development of CMEs and suggest research that may lead to more robust and flexible designs for this type of computational model.
From driving, flying, and swimming, to digging for unknown objects in space exploration, autonomous robots take on varied shapes and sizes. In part, autonomous robots are designed to perform tasks that are too dirty, dull, or dangerous for humans. With nontrivial autonomy and volition, they may soon claim their own place in human society. These robots will be our allies as we strive for understanding our natural and man-made environments and build positive synergies around us. Although we may never perfect replication of biological capabilities in robots, we must harness the inevitable emergence of robots that synchronizes with our own capacities to live, learn, and grow. This book is a snapshot of motivations and methodologies for our collective attempts to transform our lives and enable us to cohabit with robots that work with and for us. It reviews and guides the reader to seminal and continual developments that are the foundations for successful paradigms. It attempts to demystify the abilities and limitations of robots. It is a progress report on the continuing work that will fuel future endeavors.
The academic journey to a widely acknowledged Machine Consciousness is anticipated to be an emotional one. Both in terms of the active debate provoked by the subject and a hypothesized need to encapsulate an analogue of emotions in an artificial system in order to progress towards machine consciousness. This paper considers the inspiration that the concepts related to emotion may contribute to cognitive systems when approaching conscious-like behavior. Specifically, emotions can set goals including balancing explore versus exploit, facilitate action in unknown domains and modify existing behaviors, which are explored in cognitive robotics experiments.
We present an intuitive and very easy to use implicit gesture based identification system that is especially suited for security-wise non-critical applications, such as the user login in the multimedia services. The term “implicit gesture” in our work refers to a natural physical hand manipulation performed by the user who takes hold of the control device and simply picks it up from its neutral motionless position - a “pick-up” gesture. For reference with other related systems, explicit and well defined personal name identification gestures were used as well. User evaluation study results show that 100% recognition accuracy was achieved when using explicit identification signature gestures and over 91% recognition accuracy was achieved when using the implicit “pick-up” gesture. Performance of the proposed system is comparable to results of other respectable related works when using explicit identification gestures, while also showing that implicit gesture based user identification is possible and viable.
The human factors literature on intelligent systems was reviewed in relation to the following: efficient human supervision of multiple robots, appropriate human trust in the automated systems, maintenance of human operator's situation awareness, individual differences in human–agent (H-A) interaction, and retention of human decision authority. A number of approaches—from flexible automation to autonomous agents—were reviewed, and their advantages and disadvantages were discussed. In addition, two key human performance issues (trust and situation awareness) related to H–A teaming for multirobot control and some promising user interface design solutions to address these issues were discussed. Some major individual differences factors (operator spatial ability, attentional control ability, and gaming experience) were identified that may impact H-A teaming in the context of robotics control.
See: http://link.springer.com/article/10.1007/s00146-013-0534-3
Interpretation of utterances affects an interrogator’s determination of human from machine during live Turing tests. Here we consider transcripts realised as a result of a series of practical Turing tests which were held on 23rd June 2012 at Bletchley Park, England. The focus in this paper is to consider the effects of lying and truth-telling on the human judges by the hidden entities, whether human or a machine. Turing test transcripts provide a glimpse into short text communication, the type that occurs in emails: how does the reader determine truth from the content of a stranger’s textual message? Different types of lying in the conversations are explored and the judge’s attribution of human or machine is investigated in each test
Among ethicists and engineers within robotics there is an ongoing discussion as to whether ethical robots are possible or
even desirable. We answer both of these questions in the positive, based on an extensive literature study of existing arguments.
Our contribution consists in bringing together and reinterpreting pieces of information from a variety of sources. One of
the conclusions drawn is that artifactual morality must come in degrees and depend on the level of agency, autonomy and intelligence
of the machine. Moral concerns for agents such as intelligent search machines are relatively simple, while highly intelligent
and autonomous artifacts with significant impact and complex modes of agency must be equipped with more advanced ethical capabilities.
Systems like cognitive robots are being developed that are expected to become part of our everyday lives in future decades.
Thus, it is necessary to ensure that their behaviour is adequate. In an analogy with artificial intelligence, which is the
ability of a machine to perform activities that would require intelligence in humans, artificial morality is considered to
be the ability of a machine to perform activities that would require morality in humans. The capacity for artificial (artifactual)
morality, such as artifactual agency, artifactual responsibility, artificial intentions, artificial (synthetic) emotions,
etc., come in varying degrees and depend on the type of agent. As an illustration, we address the assurance of safety in modern
High Reliability Organizations through responsibility distribution. In the same way that the concept of agency is generalized in the case of artificial agents, the concept of moral agency, including responsibility, is generalized too. We propose to look at artificial moral agents as having functional responsibilities within a network
of distributed responsibilities in a socio-technological system. This does not take away the responsibilities of the other
stakeholders in the system, but facilitates an understanding and regulation of such networks. It should be pointed out that
the process of development must assume an evolutionary form with a number of iterations because the emergent properties of
artifacts must be tested in real world situations with agents of increasing intelligence and moral competence. We see this
paper as a contribution to the macro-level Requirement Engineering through discussion and analysis of general requirements
for design of ethical robots.
KeywordsArtificial morality–Machine ethics–Machine morality–Roboethics–Autonomous agents–Artifactual responsibility–Functional responsibility
Emotions have always been a complex phenomenon and research on their causes and effects have been fraught with debates. Though a reasonable and unified theory seems lacking, there have been many attempts at building models that emote. This paper describes a multi-agent approach that aids robot emotion. Emotions are grounded on percepts from sensors and generated by dedicated emotion agents that work concurrently with others – the positive suppressing the negative and vice versa while stimulating their own kinds. Each agent forms a metaphor of an emotion-generating entity that has a replenishing capability. Both the replenishing of an emotion resource and the sampling of the environment are based on fuzzy logic. Sampling of the percepts from the sensors is based on an adrenaline-like effect. Stimulations, suppressions, emotion resource, and a look-back before decay feature embed a deep and dynamic emotional milieu into a machine. The paper presents and discusses how three emotions churned from percepts gathered by a robot act as an emotional control juice capable of governing the manner of its motion along a path.
Autonomy is a prime issue on robotics field and it is closely related to decision making. Last researches on decision making for social robots are focused on biologically inspired mechanisms for taking decisions. Following this approach, we propose a motivational system for decision making, using internal (drives) and external stimuli for learning to choose the right action. Actions are selected from a finite set of skills in order to keep robot’s needs within an acceptable range. The robot uses reinforcement learning in order to calculate the suitability of every action in each state. The state of the robot is determined by the dominant motivation and its relation to the objects presents in its environment.
The used reinforcement learning method exploits a new algorithm called Object Q-Learning. The proposed reduction of the state space and the new algorithm considering the collateral effects (relationship between different objects) results in a suitable algorithm to be applied to robots living in real environments.
In this paper, a first implementation of the decision making system and the learning process is implemented on a social robot showing an improvement in robot’s performance. The quality of its performance will be determined by observing the evolution of the robot’s wellbeing.
Humans dispose of two intertwined information processing pathways, cognitive information processing via neural firing patterns and diffusive volume control via neuromodulation. The cognitive information processing in the brain is traditionally considered to be the prime neural correlate of human intelligence, clinical studies indicate that human emotions intrinsically correlate with the activation of the neuromodulatory system.
We examine here the question: Why do humans dispose of the diffusive emotional control system? Is this a coincidence, a caprice of nature, perhaps a leftover of our genetic heritage, or a necessary aspect of any advanced intelligence, being it biological or synthetic?
We argue here that emotional control is necessary to solve the motivational problem, viz the selection of short-term utility functions, in the context of an environment where information, computing power and time constitute scarce resources.
The primary tasks of a cognitive system is to survive and to maximize a life-long utility function, like the number of offsprings. A direct computational maximization of life-long utility is however not possible in complex environments, especially in the context, of real-world time constraints. The central role of emotions is to serve as an intermediate layer in the space of policies available to agents and animals, leading to a large dimensional reduction of complexity. We review our current understanding of the functional role of emotions, stressing the role of the neuromodulators mediating emotions for the diffusive homeostatic control system of the brain. We discuss a recent proposal, that emotional diffusive control is characterized, in contrast to neutral diffusive control, by interaction effects, viz by interferences between emotional arousal and reward signaling. Several proposals for the realization of synthetic emotions are discussed in this context, together with key open issues regarding the interplay between emotional motivational drives and diffusive control. Comment: A review. Cognitive Computation (in press)
ResearchGate has not been able to resolve any references for this publication.