This article presents a biologically inspired model for motor skills imitation. The model is composed of modules whose functinalities are inspired by corresponding brain regions responsible for the control of movement in primates. These modules are high-level abstractions of the spinal cord, the primary and premotor cortexes (M1 and PM), the cerebellum, and the temporal cortex. Each module is modeled at a connectionist level. Neurons in PM respond both to visual observation of movements and to corresponding motor commands produced by the cerebellum. As such, they give an abstract representation of mirror neurons. Learning of new combinations of movements is done in PM and in the cerebellum. Premotor cortexes and cerebellum are modeled by the DRAMA neural architecture which allows learning of times series and of spatio-temporal invariance in multimodal inputs. The model is implemented in a mechanical simulation of two humanoid avatars, the imitator and the imitatee. Three types of sequences learning are presented: (1) learning of repetitive patterns of arm and leg movements; (2) learning of oscillatory movements of shoulders and elbows, using video data of a human demonstration; 3) learning of precise movements of the extremities for grasp and reach

Abstract not found

Designing a mechanism that will allow a robot to imitate the actions of a human, apart from being interesting for opening the possibilities for efficient social learning through observation and imitation, is challenging since it requires the integration of information from the visual, memory and motor systems. This paper deals with the implementation of an imitation architecture on an active, stereo vision head, and describes our experiments on the deferred imitation of human head movements. 1 Introduction Robots of the near future are expected to operate among humans, who will want them to not only function effectively, safely and with minimum discomfort to their users, but to be able to learn and adapt to their particular lifestyle. Preprogramming robots with specific task solving capabilities and individual trial and error learning can only get them up to a certain level of competence. The ability to learn based on observation and interaction with other agents in their environment...

... this paper demonstrates scaling up of this movement imitative strategy for transmitting a vocabulary across a group of robotic agents, i.e. from a teacher agent to several learner agents. In particular, it shows that imitative behaviour is necessary for the grounding of the agents' proprioceptions and speeds up the grounding of exteroceptions. These studies stress the importance of behavioural social mechanisms in addition to general cognitive abilities of associativity for grounding communication in embodied agents. In particular, it shows that a simple movement imitation strategy is an interesting scenario for the transmission of a language, as it is an easy means of getting the agents to share a common context of perceptions, which is a prerequisite for a common understanding of the language to develop. It is thus suggested that a behaviour -oriented approach might be more appropriate than a pure cognitivist one which is dominating in related studies of the mechanisms involved in grounding communication.

The identification of any form of social learning, imitation, copying or mimicry presupposes a notion of correspondence between two autonomous agents. Judging whether a behavior has been transmitted socially requires the observer to identify a mapping between the demonstrator and the imitator. If the demonstrator and imitator have similar bodies, e.g. are animals of the same species, of similar age, and of the same gender, then to a human observer an obvious correspondence is to map the corresponding body parts: left arm of demonstrator maps to left arm of imitator, right eye of demonstrator maps to right eye of imitator, tail of demonstrator maps to tail of imitator. There is also an obvious correspondence of actions: raising the left arm by the model corresponds to raising the left arm by the imitator, production of vocal signals by the model corresponds to the production of acoustically similar ones by the imitator, picking up a fruit by the demonstrator corresponds to picking up a fruit of the same type by the imitator. Furthermore, there is a correspondence in sensory experience: audible sounds, a touch, visible objects and colors, and so on evidently seem to be detected and experienced in similar ways. What to take as the correspondence seems relatively clear in this case. As humans, we are good at imitating and at recognizing such correspondences. It is also clear that most other animals, robots, and software programs may in fact generally fail to recognize any such correspondences. To judge a produced behavior to be a copy of an observed one, we require at least that it respects some such correspondence. The faithfulness or precision of the behavioral match can obviously vary, and no absolute cutoff or threshold exists defining success as opposed to failure of behavioral matching. But one can study the degree of success using various metrics and measures of correspondence (Nehaniv & Dautenhahn, 2001; also see below). Moreover, it turns out that the “obvious” correspondences between similar bodies mentioned above are not the only ones possible. Consider a human imitating another one that is facing her: if the demonstrator raises her left arm, should the imitator raise her own left arm? Or should she raise her right, to make a "mirror image" of the demonstrator's actions? If the demonstrator picks up a brush, should an imitator pick up the same brush? Or just another brush of the same type? If the demonstrator opens a container to get at chocolate inside, should the imitator open a similar container in the same way – e.g. by unwrapping but not tearing the surrounding paper?, or is it enough just to open the container somehow? The different possible answers to these questions presuppose different correspondences. If a child watches a teacher solving subtraction problems in arithmetic, and then solves for the first time similar but not identical problems on its own, social learning has occurred. But what type of correspondence is at work here? In China and Japan, the ideographic character for “to imitate” also means “to learn” or “to study”. By going through the motions of an algorithm for solving sample problems, students everywhere are able to learn how to solve similar ones, of course without necessarily gaining understanding of why the procedures they have learned work. In this chapter, for lack of a better term, we shall use the word “imitator” to refer to any autonomous agent performing a candidate behavioral match. The use of this word here does not entail any particular mechanism of matching or any particular type of social learning. In what follows, we shall describe how different matching phenomena arise depending on the criteria employed in generating the behavior of the imitator. For example, goal emulation, stimulus enhancement, mimicry, and so on, will all be cast as solutions to correspondence problems with different particular selection criteria.

Therapeutic and educational applications of robots have created a demand for robots showing a number of social skills. These skills include the capacity to imitate, to learn from demonstration, to interpret gestures and to recognize speech. Robot toys are an ideal platform to investigate the potential and limitations of human–robot social interactions. This paper presents Robota, a mini-humanoid doll-shaped robot. Robota is used in an introductory robotics class at the undergraduate level. The class offers an introduction to different tools necessary for building human–robot social interactions. Through a series of hands-on projects, students learn how to use vision and speech processing and how to design learning algorithms. The goal of each project is to create an educational and entertaining game for normal and disabled children.

Introduction This chapter presents the agent-based perspective on imitation. In this perspective, imitation is best considered as the behavior of an autonomous agent in relation to its environment, including other autonomous agents. We argue that such a perspective helps unfold the full potential of research on imitation and helps in identifying challenging and important research issues. We first explain the agent-based perspective and then discuss it in the context of particular research issues in studies with animals and artifacts, with reference to chapters presented in this book. At the end of the chapter we briefly introduce the individual contributions to this book and provide a roadmap that helps the reader in navigating through the exciting and highly interwoven themes that are presented in this book. In order to focus discussions, we explain the agent-based perspective with particular consideration of the correspondence

Abstract not found

The causal chains of culture Members of a human group are bound with one another by multiple flows of information. (Here we use “information ” in a broad sense that includes not only the content of people’s knowledge, but also that of their beliefs, assumptions, fictions, rules, norms, skills, maps, images, and so on.) This information is materially realized in the mental representations of the people, and in their public productions, that is, their cognitively guided behaviors and the enduring material traces of these behaviors. Mentally represented information is transmitted from individuals to individuals through public productions. Public representations such as speech, gestures, writing, or pictures are a special type of public productions, the function of which is to communicate a content. Public representations play a major role in information transmission. Much information, however, is communicated implicitly, that is, without being publicly represented. Information can also be transmitted without being properly speaking communicated, not even implicitly, as when one individual acquires a skill by observing and imitating the behavior of others. Most information transmitted among humans is about local and transient circumstances, and is not transmitted beyond these. Some information of more general relevance, however, is repeatedly transmitted, and propagates throughout the group. Talk of “culture ” (whatever the preferred definition or theory of culture) is about this widely distributed information and about its material realizations inside people’s mind and in their common environment (see Sperber 1996). One can study cultural phenomena in two main ways. One can interpret them, that is, try and make their contents intelligible to people of

Abstract. A laboratory experiment was conducted in order to explore the possibility of imitation, that is, response learning by observation, in marmosets, Callithrix jacchus. Inexperienced individuals were allowed to observe a skilful model that demonstrated one of two possible techniques (pushing or pulling a pendulum-door) to get food from inside a wooden box. Their initial manipulative actions, performed when exposed to the box in a subsequent test, were compared with those of naive control subjects (non-observers). The observers showed less exploratory behaviour than the non-observers and, more importantly, some showed a strong tendency to use the demonstrated opening technique in the initial test phase. This initial preference disappeared in the course of five test sessions and the observers converged towards the simpler, alternative solution that was generally preferred by the non-observers. Despite fundamental individual differences in the observer group and the failure to find a significant group effect, the results indicate that marmosets are capable of learning simple motor skills through conspecific observation. � 1997 The Association for the Study of Animal Behaviour The basic tenet of the social (‘Machiavellian’) intelligence hypothesis is that, although most