Search

In this study we investigated the effects of different morphological configurations on a robot swinging task using van der Pol oscillators. The task was examined using two separate degrees of freedom (DoF), both in the presence and absence of neural entrainment. Neural entrainment stabilises the system, reduces time-to-steady state and relaxes the requirement for a strong coupling with the environment in order to achieve mechanical entrainment. It was found that staged release of the distal DoF does not have any benefits over using both DoF from the onset of the experimentation. On the contrary, it is less efficient, both with respect to the time needed to reach a stable oscillatory regime and the maximum amplitude it can achieve. The same neural architecture is successful in achieving neuromechanical entrainment for a robotic walking task.

How does an individual use the knowledge acquired through self exploration as a manipulable model through which to understand others and benefit from their knowledge? How can developmental and social learning be combined for their mutual benefit? In this paper we review a hierarchical architecture (HAMMER) which allows a principled way for combining knowledge through exploration and knowledge from others, through the creation and use of multiple inverse and forward models. We describe how Bayesian Belief Networks can be used to learn the association between a robot’s motor commands and sensory consequences (forward models), and how the inverse association can be used for imitation. Inverse models created through self exploration, as well as those from observing others can coexist and compete in a principled unified framework, that utilises the simulation theory of mind approach to mentally rehearse and understand the actions of others.

This paper describes our model of the emergence of a mirror system for imitative learning. The mirror system is an intermodal mapping between someone's action (as seen) and one's own action (to execute). It is widely assumed that the mapping is a geometric transformation between bodies in the visual and motor spaces; however, it is still unclear if the mapping is innate or, if not, how it is acquired. We claim here that the mapping is not a geometric transformation between bodies but a functional correspondence between someone's action on an object for producing an effect and one's own action on the same or similar object for producing a similar effect, which is learnable because both tend to utilize the object's affordance in a similar way.

In this paper we try to locate the essential components needed for a developmental robot architecture. We take the vocabulary and the main concepts from Piaget’s genetic epistemology and Vygotsky’s activity theory. After proposing an outline for a general developmental architecture, we describe the architectures that we have been developing in the recent years - Petitagé and Vygovorotsky. According to this outline, various contemporary works in autonomous agents can be classified, in an attempt to get a glimpse into the big picture and make the advances and open problems visible.

The global dynamics, a novel concept for design of human/humanoid behavior is proposed. The principle of this concept is to exploit the body dynamics and apply control input only where it is necessary. Within the phase space of the body dynamics, there are many stable and unstable mani-folds coexist. Then if we analysed its structure and obtained a map in sufficient resolution, it may be possible to realise a motion by exploiting stable regions for reducing control input and unstable regions for switching between stable regions. Also, we expect an emergence of symbols within the dynamics, as the series of points where control input should be adopted. This feature realises higher level description and makes adaptation behavior easier. We are studying from two aspects, the motion capture experiment and dynamical simulation of simple elastic robot. The former supports that above assumption and the latter supports the exploiting the dynamical stability is useful.

We present three humanoid robots aimed as platforms for research in robotics, and cognitive development in robotics systems. The 'priscilla' robot is a 180cm full scale humanoid, and the mid-size prototype is called 'elvis' and is about 70cm tall. The smallest size humanoid is the 'elvina' type, about 28 cm tall. Two instances of 'elvina' have been built to enable experiments with cooperating humanoids. The underlying ideas and conceptual principles, such as anthropomorphism, embodiment, and mechanisms for learning and adaptivity are introduced as well.

It has been proved to be extremely challenging for humans to program a robot to such a sufficient degree that it acts properly in a typical unknown human environment. This is especially true for a humanoid robot due to the very large number of redundant degrees of freedom and a large number of sensors that are required for a humanoid to work safely and effectively in the human environment. How can we address this fundamental problem? Motivated by human mental development from infancy to adulthood, we present a theory, an architecture, and some experimental results showing how to enable a robot to develop its mind automatically, through online, real time interactions with its environment. Humans mentally “raise” the robot through “robot sitting” and “robot schools” instead of task-specific robot programming.

We describe robot navigation learning based on self-selection of privileged vectors through the environment in accordance with an in built economy metric. This provides the opportunity both for progressive behavioural adaptation, and adaptive derivations, leading, through situated activity, to “representations" of the environment which are both economically attained and inherently meaningful to the agent.

We are exploring the idea that early language acquisition could be better modelled on an artifcial creature by considering the pragmatic aspect of natural language and of its development in human infants. We have implemented a system of vocal behaviors on Kismet in which "words" or concepts are behaviors in a competitive hierarchy. This paper reports on the framework, the vocal system's architecture and algorithms, and some preliminary results from vocal label learning and concept formation.

How to represent own body is one of the most interesting issues in cognitive developmental robotics which aims to understand the cognitive developmental processes that an intelligent robot would require and how to realize them in a physical entity. This paper presents a cognitive model how the robot acquires its own body representation, that is body scheme for the body surface. The internal observer assumption makes it difficult for a robot to associate the sensory information from different modalities because of the lacking of references between them that are usually given by the designer in the prenatal stage of the robot. Our model is based on cross-modal map learning among join, vision, and tactile sensor spaces by associating different pairs of sensor values when they are activated simultaneously. We show a preliminary experiment, and then discuss how our model can explain the reported phenomenon on body scheme and future issues.

We suppose the functional parts combination (FPC) model, whereby a problem solving strategy is acquired depending on the tasks given. The model is based on the neuroscientific fact that each cerebral cortical area has a different role and is selectively activated depending on the task. FPC model is a meta learning model that consists of a set of functional parts and a sequence of control signals that specifies their combination. The functional parts are combined depending on the situation, to realize a processing circuit required for the situation. We use genetic algorithm for searching the control signals. We examine the model by evaluating the difference in acquired behavior of (1) two agents with different functional parts working on the same navigational task and (2) two agents with the same functional parts working on different tasks. We show that the agent using FPC model acquires learning strategies suitable for the given problems.

We present experiments in which a group of autonomous mobile robots learn to perform fundamental sensor-motor tasks through a collaborative learning process. Behavioural strategies, i.e. motor responses to sensory stimuli, are encoded by means of genetic strings stored on the individual robots, and adapted through a genetic algorithm (Mitchell, 1998) executed by the entire robot collective: robots communicate their own strings and corresponding fitness to each other, and then execute a genetic algorithm to improve their individual behavioural strategy. The robots acquired three different sensormotor competences, as well as the ability to select one of two, or one of three behaviours depending on context ("behaviour management"). Results show that fitness indeed increases with increasing learning time, and the analysis of the acquired behavioural strategies demonstrates that they are effective in accomplishing the desired task.

For the purposes of manipulation, we would like to know what parts of the environment are physically coherent ensembles - that is, which parts will move together, and which are more or less independent. It takes a great deal of experience before this judgement can be made from purely visual information. This paper develops active strategies for acquiring that experience through experimental manipulation, using tight correlations between arm motion and optic flow to detect both the arm itself and the boundaries of objects with which it comes into contact. We argue that following causal chains of events out from the robot's body into the environment allows for a very natural developmental progression of visual competence, and relate this idea to results in neuroscience.

An automatic choreography method to generate lifelike body movements is proposed. This method is based on somatics theories that are conventionally used to evaluate human’s psychological and developmental states by analyzing the body movement. The idea of this paper is to use the theories in the inverse way: to facilitate generation of artificial body movements that are plausible regarding evolutionary, developmental and emotional states of robots or other non-living movers. This paper reviews somatic theories and describes a strategy for implementations of automatic body movement generation. In addition, a psychological experiment is reported to verify expression ability on body movement rhythm. This method facilitates to choreographing body movement of humanoids, animal-shaped robots, and computer graphics characters in video games.

We present a system that attempts to model the functional role of mirror neurons, namely the activation of structures in response to both the observation of a demonstrated task, and its generation. Through social situatedness and a set of innate skills, perceptual and motor structures develop for recognition and reproduction of demonstrated actions. We believe this is an implementation towards a mirror system, and we test it on two platforms, one in simulation involving imitation of object interactions, the second on a physical robot learning from a human to follow walls.

The concept of ‘social situatedness’, i.e. the idea that the development of individual intelligence requires a social (and cultural) embedding, has recently received much attention in cognitive science and artificial intelligence research. The work of Lev Vygotsky who put forward this view already in the 1920s has influenced the discussion to some degree, but still remains far from well known. This paper therefore aims to give an overview of his cognitive development theory and discuss its relation to more recent work in primatology and socially situated artificial intelligence, in particular humanoid robotics.

Given a neural control structure, what would be the impact of body growth on control performance? This question, which addresses the issue of the interaction between innate structure, ongoing developing structure and experience, is very relevant to the field of epigenetic robotics. Much of the early social interaction is done as the body develops and the interplay cannot be ignored. We hypothesize that starting with fewer degrees of freedom enables a more efficient exploration of the sensorimotor space, that results in multiple directions of stability. While not necessarily corresponding to optimal task performance, they will guide the coordination of additional degrees of freedom. These additional degrees of freedom then allow for optimal task performance as well as for more tolerance and adaptation to environmental interaction. We propose a simple case-study to validate our hypothesis and describe experiments with a small humanoid robot.

The value system of a developmental robot signals the occurrence of salient sensory inputs, modulates the mapping from sensory inputs to action outputs, and evaluates candidate actions. In the work reported here, a low level value system is modeled and implemented. It simulates the non-associative animal learning mechanism known as habituation effect. Reinforcement learning is also integrated with novelty. Experimental results show that the proposed value system works as designed in a study of robot viewing angle selection.

Science, like any other cognitive activity, is grounded in the sensorimotor interaction of our bodies with the environment. Human embodiment thus constrains the class of scientific concepts and theories which are accessible to us. The paper explores the possibility of doing science with artificial cognitive agents, in the framework of an interactivist-constructivist cognitive model of science. Intelligent robots, by virtue of having different sensorimotor capabilities, may overcome the fundamental limitations of human science and provide important technological innovations. Mathematics and nanophysics are prime candidates for being studied by artificial scientists.

A crucial aspect of the development of language in children has been concerned with pragmatics - a field which explores the ways in which interaction is successfully accomplished. One aspect of this is concerned with the sequential implicativeness of our actions - that is what do particular behaviours accomplish given the specific turn by turn interactive sequence in which they occur. This paper seeks to consider some aspects of this by reference to conversation analytic work on gaze in adult interaction. In this way the paper attempts to provide a brief overview of some of the ways that our thinking about robot - human interaction can be deepened by an appreciation of conversation analytic work. In particular it argues that the empirical basis of conversation analysis (henceforth CA) offers a wonderful treasure-trove of understandings about how humans accomplish social interaction. The understanding that CA provides is derived from careful empirical scrutiny and therefore it is able to offer a perspective on interaction that is sensitive to minute detail rather than crude applications of global concepts. Thus this paper provides a provisional inspection of a small fraction of CA literature concerning the use of gaze in interaction and thinks through the relevance that this might have for the design and understanding of interacting robots. Whilst CA provides a complex understanding of human interaction, predominantly derived from the everyday talk of adults, this paper argues that the approach can provide both an idealised target of communication competence and perhaps more important a means of understanding instances of human-robot interaction. In this way CA may usefully supplement other approaches to communicative competence in work on interacting robots.

In this paper we propose a description language for specifying motions for humanoid robots and for allowing humanoid robots to acquire motor skills. Locomotion greatly increases our ability to interact with our environments, which in turn increases our mental abilities. This principle also applies to humanoid robots. However, there are great difficulties to specify humanoid motions and to represent motor skills, which in most cases require four-dimensional space representations. We propose a representation framework that includes the following attributes: motion description layers, egocentric reference system, progressive quantized refinement, and automatic constraint satisfaction. We also outline strategies for acquiring new motor skills by learning from trial and error, macro approach, and programming. Then, we outline the development of a new humanoid motion description language called Cybele.

This paper discusses the concept of Volitron - a controller to make its host robot increase its competence in such activities as self-initiated exploration of an environment, new goal acquisition, and planning/executing of actions while taking into account predicted behaviors of objects of interest. There are four key elements in Volitron's structure: a model of perceived reality, a model of desired reality, a model of ideal reality and a model of anticipated reality. The task of a robot's working memory includes producing images of the robot itself imitating another subject's activities and sending the images to a model of desired reality. A tension (a concept borrowed from psychoanalysis) arising from the differences between a perceived reality and a desired reality is a source of a motivation toward action. The final decision to take an action is based on a comparison of the model of anticipated reality with that of ideal reality. The interaction of Volitron's elements are described in the paper. Furthermore, a computational model of working memory (WM) and its psychological justification are provided.

We present the first stages of the developmental course of a robot using vision and a 5 degree of freedom robotic arm. During an exploratory behavior, the robot learns visuo-motor control of its mechanical arm. We show how a simple neural network architecture, combining elementary vision, a self-organized algorithm, and dynamical Neural Fields is able to learn and use proper associations between vision and arm movements, even if the problem is ill posed (2-D toward 3-D mapping and also mechanical redundancy between different joints). Highlighting the generic aspect of such an architecture, we show as a robotic result that it is used as a basis for simple gestural imitations of humans. Finally we show how the imitative mechanism carries on the developmental course, allowing the acquisition of more and more complex behavioral capabilities.