Developmental Robotics Research Papers - Academia.edu (original) (raw)
Language and number learning in developmental robots. Developmental Robotics is the interdisciplinary approach to the autonomous design of behavioural and cognitive capabilities in artificial agents that takes direct inspiration from the... more
Language and number learning in developmental robots. Developmental Robotics is the interdisciplinary approach to the autonomous design of behavioural and cognitive capabilities in artificial agents that takes direct inspiration from the developmental principles and mechanisms observed in natural cognitive systems. This approach puts strong emphasis on constraining the robot's cognitive architecture and behavioural and learning performance onto known child psychology theories and data, allowing the modelling of the developmental succession of qualitative and quantitative stages leading to the acquisition of adult-like cognitive skills. In this paper we present a set of studies based on the developmental robotics approach looking specifically at the modelling of embodied phenomena in the acquisition of linguistic and numerical cognition capabilities.
Recent research into the nature of self in artificial and biological systems raises interest in a uniquely determining immutable sense of self, a "metaphysical 'I'" associated with inviolable personal values and moral convictions that... more
Recent research into the nature of self in artificial and biological systems raises interest in a uniquely determining immutable sense of self, a "metaphysical 'I'" associated with inviolable personal values and moral convictions that remain constant in the face of environmental change, distinguished from an object “me” that changes with its environment. Complementary research portrays processes associated with self as multimodal routines selectively enacted on the basis of contextual cues informing predictive self or world models, with the notion of the constant, pervasive and invariant sense of self associated with a multistable attractor set aiming to ensure personal integrity against threat of disintegrative change. This paper proposes that an immutable sense of self emerges as a global attractor which can be described as a project ideal self-situation embodied in frontal medial processes during more or less normal adolescent development, and that thereafter serves to orient agency in the more or less free development of embodied potentials over the life course in effort to realize project conditions, phenomenally identified with the felt pull towards this end as purpose of and source of meaning in life. So oriented, life-long self-development aims to embody solutions to problems at different timescales depending on this embodied purpose, ultimately in the service of evolutionary processes securing organism populations against threats of disintegrative change over timespans far beyond that of the individual. After characterizing the target sense of self, research circling this target is briefly surveyed. Self as global project and developmental neural correlates are proposed. Then, the paper discusses some implications for research in biological and artificial systems. Building from earlier work in cognitive neurorobotics, discussion affirms the value of reinforcement rituals including prayer in metaphysical self-development, considers implications for value alignment and rights associated with free will in the context of artificial intelligence and robot religion, and concludes by emphasizing the importance of self-development toward project ideals as source of meaning in life in the current social-political environment.
The development of artificial intelligence (AI) systems has to date been largely one of manual labor. This constructionist approach to AI has resulted in systems with limited-domain application and severe performance brittleness. No AI... more
The development of artificial intelligence (AI) systems has to date been largely one of manual labor. This constructionist approach to AI has resulted in systems with limited-domain application and severe performance brittleness. No AI architecture to date incorporates, in a single system, the many features that make natural intelligence general-purpose, including system-wide attention, analogy-making, system-wide learning, and various other complex transversal functions. Going beyond current AI systems will require significantly more complex system architecture than attempted to date. The heavy reliance on direct human specification and intervention in constructionist AI brings severe theoretical and practical limitations to any system built that way.
One way to address the challenge of artificial general intelligence (AGI) is replacing a top-down architectural design approach with methods that allow the system to manage its own growth. This calls for a fundamental shift from hand-crafting to self-organizing archi- tectures and self-generated code – what we call a constructivist AI approach, in reference to the self-constructive principles on which it must be based. Methodologies employed for constructivist AI will be very different from today’s software development methods; instead of relying on direct design of mental functions and their implementation in a cognitive architecture, they must address the principles – the “seeds” – from which a cognitive architecture can automatically grow. In this paper I describe the argument in detail and examine some of the implications of this impending paradigm shift.
When approaching eye gaze simulation in conversational agents developers tend to focus on maximum resemblance to human-like oculomotor apparatus. However, is that crucial when constructing an artificial conversational partner? Cartoon... more
When approaching eye gaze simulation in conversational agents developers tend to focus on maximum resemblance to human-like oculomotor apparatus. However, is that crucial when constructing an artificial conversational partner? Cartoon characters do not have human-like saccades or human-like eyeball structure - nevertheless, we tend to develop a greater emotional attachment to them than to a human stranger. The focus of F-2 Emotional Robot project is to create a conversational agent which may not resemble a human in its physiology but which could communicate through both verbal and body languages. This paper aims to study and model the eye gaze moderation system aimed at making F-2 Emotional Robot more attractive and natural in human-robot interaction. This project proceeds from the view of oculomotor behaviour as an information-transmitting system, consisting of intentional and spontaneous signs in communication. First, I present my analysis and description of human oculomotor conversational behaviour, a system of communicationally meaningful expressions, on the basis of the Russian Emotional Corpus. Next, I implement the suggested model in the robot. I prove the significance of eye gaze in human-robot interaction through a short evaluation experiment. As a final step of my research, I assess perception of resulting eye gaze moderating system by means of user-experience testing within human-robot interaction. The resulting eye gaze model is not exclusively tailored to F-2 Emotional Robots, it can be used as a theoretical basis for constructing eye gaze behaviour in conversational interfaces in general. My research presents the practical implementation of eye gaze behaviour in F-2 Emotional Robot, as well as contributes to the broader field of study of the non-verbal communication systems.
Develop a unique Virtual Teach Pendant using LabVIEW for eliminating the need of a hard wired Teach Pendant genreally present in an Industrial Manipulator System. This Teach Pendant vi has 3 modes and is open sourced and can be programmed... more
Develop a unique Virtual Teach Pendant using LabVIEW for eliminating the need of a hard wired Teach Pendant genreally present in an Industrial Manipulator System. This Teach Pendant vi has 3 modes and is open sourced and can be programmed according to the need of the application for the system, so by just changing the software on the teach pendant we can make the Robotic system perform versatile operations like pick-place, painting, welding, cutting, etc
The design of a system that bootstraps an open-ended development is one of the most intriguing questions in Developmental Robotics. Inspired by evolution we propose an incremental design. We start with a reac- tive layer that provides... more
The design of a system that bootstraps an open-ended development is one of the most intriguing questions in Developmental Robotics. Inspired by evolution we propose an incremental design. We start with a reac- tive layer that provides task-unspecific inter- action with the environment. We extend this initial layer by a layer of multi-modal expec- tation generation. The two layers are coupled by means of an active resolution of expecta- tion mismatches. Such an extension allows for the transition from reactive behavior to hypothesis testing and goal-directed behavior. The expectations can also be used as a teach- ing signal. The proposed architecture is vali- dated on the example of multi-modal learning and evaluation of auditory labels tested on the humanoid robot Asimo.
Some artificial intelligence research applies theories about self and consciousness in design and interpretation of computational modeling experiments. However, different senses of self remain unresolved in natural systems, hindering... more
Some artificial intelligence research applies theories about self and consciousness in design and interpretation of computational modeling experiments. However, different senses of self remain unresolved in natural systems, hindering progress in biologically inspired computational models. Recent work distinguishes between "me" and "I", locates "me" in layers of neurological activity, and challenges researchers to locate the "metaphysical 'I'" in the natural order, similarly. How might such a sense of self emerge in human beings, and what are the implications for AI research? This paper locates the "I" as a global project emerging through more or less normal adolescent development, and towards the realization of which neural processes associated with intermediate tasks grow, organize and are preferentially enacted. Discussion concludes by briefly noting implications for ongoing research into self in humans, in AI, their mutual value alignment and the relative moral status of systems engineered accordingly.
Just as human-human behavior and interactions are important to study, human-robot interactions will take more prominence in the near future. These interactions will not only be in one direction, robots helping humans, but they will also... more
Just as human-human behavior and interactions are important to study, human-robot interactions will take more prominence in the near future. These interactions will not only be in one direction, robots helping humans, but they will also be bidirectional with humans helping robots. This study examined the interactions between children and robots by observing whether children help a robot complete a task, and the contexts which elicited the most help. Five studies were conducted each consisting of 20 or more children per group with an approximate even number of boys and girls. Visitors to a science centre located in a major Western Canadian city were invited to participate in an experiment set up at the centre. Their behaviors with a robot, a small 5 degree of freedom robot arm programmed with a set of predefined tasks which could be selected during the experiments, were observed. Results of chi-square analyses indicated that children are most likely to help a robot after experiencing a positive introduction to it, X 2(1)=4.15,p=.04. Moreover, a positive introduction in combination with permission to help resulted in the vast majority (70%) of children helping. These results suggest that adult instructions about a robot impact children’s perceptions and helping behaviors towards it. The generalizability of these results to children’s helping behaviors towards people is also discussed.
The basis of a humane approach to others is the authentic comprehension of another subject. As humans, we can achieve this understanding well, and the reason lies in how we experience the world around us and other subjects in it. The... more
The basis of a humane approach to others is the authentic comprehension of another subject. As humans, we can achieve this understanding well, and the reason lies in how we experience the world around us and other subjects in it. The development of robots capable of socially interacting and helping humans is progressing, even though they are still far from reaching an autonomous comprehension of others' intentions, emotions, and feelings. In this sense, the humane approach may be addressed in robotics through the concept of experience. In a reciprocal exchange of perspectives, the core elements and the structure of human experience are investigated in this chapter together with how the idea of experience has been implemented in robots. The embodied Self and the relationship with other subjects form the pivot of any human experience and are suggested to be the basis for the emergence of a novel cognitive-experiential structure in robots. Conversely, the possibility to develop a robot with a primitive sense of Self raises questions about the nature of human experience and the impact such technologies have on it.
Research on anticipatory behavior in adaptive learning systems continues to gain more recognition and appreciation in various research disciplines. This book provides an overarching view on anticipatory mechanisms in cognition, learning,... more
Research on anticipatory behavior in adaptive learning systems continues to gain more recognition and appreciation in various research disciplines. This book provides an overarching view on anticipatory mechanisms in cognition, learning, and behavior. It connects the knowledge from cognitive psychology, neuroscience, and linguistics with that of artificial intelligence, machine learning, cognitive robotics, and others. This introduction offers an overview over the contributions in this volume highlighting their interconnections and interrelations from an anticipatory behavior perspective. We first clarify the main foci of anticipatory behavior research. Next, we present a taxonomy of how anticipatory mechanisms may be beneficially applied in cognitive systems. With relation to the taxonomy, we then give an overview over the book contributions. The first chapters provide surveys on currently known anticipatory brain mechanisms, anticipatory mechanisms in increasingly complex natural languages, and an intriguing challenge for artificial cognitive systems. Next, conceptualizations of anticipatory processes inspired by cognitive mechanisms are provided. The conceptualizations lead to individual, predictive challenges in vision and processing of event correlations over time. Next, anticipatory mechanisms in individual decision making and behavioral execution are studied. Finally, the book offers systems and conceptualizations of anticipatory processes related to social interaction.
Learning and interaction are viewed as two related but distinct topics in developmental robotics. Many studies focus solely on either building a robot that can acquire new knowledge and learn to perform new tasks, or designing smooth... more
Learning and interaction are viewed as two related but distinct topics in developmental robotics. Many studies focus solely on either building a robot that can acquire new knowledge and learn to perform new tasks, or designing smooth human-robot interactions with pre-acquired knowledge and skills. The present paper focuses on linking language learning with human-robot interaction, showing how better human-robot interaction can lead to better language learning by robot. Toward this goal, we developed a real-time human-robot interaction paradigm in which a robot learner acquired lexical knowledge from a human teacher through free-flowing interaction. With the same statistical learning mechanism in the robot's system, we systematically manipulated the degree of activity in human-robot interaction in three experimental conditions: the robot learner was either highly active with lots of speaking and looking acts, or moderately active with a few acts, or passive without actions. Our results show that more talking and looking acts from the robot, including those immature behaviors such as saying nonsense words or looking at random targets, motivated human teachers to be more engaged in the interaction. In addition, more activities from the robot revealed its robot's internal learning states in real time, which allowed human teachers to provide more useful and " on-demand " teaching signals to facilitate learning. Thus, compared with passive and batch-mode training, an active robot learner can create more and better training data through smooth and effective social interactions that consequentially lead to more successful language learning.
This paper reports on a developmental approach to the learning of communication in embodied agents, taking inspiration from child development and recent advances in the understanding of the mirror neuron system within the brain. We... more
This paper reports on a developmental approach to the learning of communication in embodied agents, taking inspiration from child development and recent advances in the understanding of the mirror neuron system within the brain. We describe a part of the ROSSI project which focuses upon gestural communication in the form of pointing. We are examining the idea that pointing may be a key step towards simple spoken communication and exploring the internal representations that may be formed during this process. The possible developmental stages leading to proto-imperative pointing actions in a robotic system are outlined, and how this may be built upon to result in an understanding of two word speech is discussed. The learning mechanism is based around Piagetian schema learning whilst the developmental path follows a mixture of Piagetian and Vygotskian theories.
This paper presents a computational theory of developmental mental architectures for artificial and natural systems, motivated by neuroscience. The work is an attempt to approximately model biological mental architectures using... more
This paper presents a computational theory of developmental mental architectures for artificial and natural systems, motivated by neuroscience. The work is an attempt to approximately model biological mental architectures using mathematical tools. Six types of architecture are presented, beginning with the observation-driven Markov decision process as Type-1. From Type-1 to Type-6, the architecture progressively becomes more complete toward the necessary
Intrinsic motivation, centrally involved in spontaneous exploration and curiosity, is a crucial concept in developmental psychology. It has been argued to be a crucial mechanism for open-ended cognitive development in humans, and as such... more
Intrinsic motivation, centrally involved in spontaneous exploration and curiosity, is a crucial concept in developmental psychology. It has been argued to be a crucial mechanism for open-ended cognitive development in humans, and as such has gathered a growing interest from developmental roboticists in the recent years. The goal of this paper is threefold. First, it provides a synthesis of the different approaches of intrinsic motivation in psychology. Second, by interpreting these approaches in a computational reinforcement learning framework, we argue that they are not operational and even sometimes inconsistent. Third, we set the ground for a systematic operational study of intrinsic motivation by presenting a formal typology of possible computational approaches. This typology is partly based on existing computational models, but also presents new ways of conceptualizing intrinsic motivation. We argue that this kind of computational typology might be useful for opening new avenues for research both in psychology and developmental robotics.