Search

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.

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.

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.

While computational models are playing an increasingly important role in developmental psychology, at least one lesson from robotics is still being learned: modeling epigenetic processes often requires simulating an embodied, autonomous organism. This paper first contrasts prevailing models of infant cognition with an agent-based approach. A series of infant studies by Baillargeon (1986; Baillargeon & DeVos, 1991) is described, and an eye-movement model is then used to simulate infants' visual activity in this study. I conclude by describing three behavioral predictions of the eyemovement model, and discussing the implications of this work for infant cognition research.

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.

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.

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.

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.