This paper proposes a research direction to study the development of `artificial social intelligence' of autonomous robots which should result in `individualized robot societies'. The approach is highly inspired by the `social intelligence hypothesis', derived from the investigation of primate societies, suggesting that primate intelligence originally evolved to solve social problems and was only later extended to problems outside the social domain. We suggest that it might be a general principle in the evolution of intelligence, applicable to both natural and artificial systems. Arguments are presented why the investigation of social intelligence for artifacts is not only an interesting research issue for the study of biological principles, but may be a necessary prerequisite for those scenarios in which autonomous robots are integrated into human societies, interacting and communicating both with humans and with each other. As a starting point to study experimentally the development ...

Adults conceptualize the world in terms of enduring physical objects...

. We do not exist alone. Humans and most other animal species live in societies where the behaviour of an individual influences and is influenced by other members of the society. Within societies, an individual learns not only through classical conditioning and reinforcement, but to a large extent through observation and imitation. This paper presents an analysis of the problem of adding such imitative learning abilities to mobile robots and describes a biologically-inspired architecture we are developing for imitative learning. Our robotic testbed and learning experiments are described and discussed. 1 Introduction Interest in the field of robot learning has been growing steadily in the last few years. Adding learning abilities to robots offers certain distinct benefits, such as ffl Increasing their ability to cope with a dynamic environment where preprogrammed knowledge of the world can become obsolete or is not available at all in the first place. ffl Reducing the cost of program...

Imitation is a mechanism for the intergenerational transmission of acquired characteristics. Before explicit linguistic instruction, infants learn many of the skills, customs, and behaviour patterns of their culture through imitation. In imitating, infants use another's behaviours as a basis for their own, despite differences in body size, perspective of view, and modality through which self and other can be perceived. As ubiquitous and useful as imitation is, how imitation is accomplished poses one of the deeper puzzles in infancy.

Imitation represents a useful and promising alternative to programming robots. The approach presented here is based on two functional elements used by humans to understand and perform actions. These elements are: the body schema and the body percept. The first one is a representation of the body containing information of the body's capabilities. The body percept is a snapshot of the body and its relation with the environment at a given instant. These elements are believed to interact between each other generating among other abilities, the ability to imitate. This paper presents our approach to robot imitation and experimental results, where a robot is able to imitate the movements of a human demonstrator via its visual observations.

Evolutionary developmental psychology involves the expression of evolved, epigenetic programs, as described by the developmental systems approach, over the course of ontogeny. There have been different selection pressures on organisms at different times in ontogeny, and some characteristics of infants and children were selected in evolution to serve an adaptive function at that time in their life history rather than to prepare individuals for later adulthood. Examples of such adaptive functions of immaturity are provided from infancy, play, and cognitive development. Most evolved psychological mechanisms are proposed to be domain specific in nature and have been identified for various aspects of children’s cognitive and social development, most notably for the acquisition of language and for theory of mind. Differences in the quality and quantity of parental investment affect children’s development and influence their subsequent reproductive and childcare strategies. Some sex differences observed in childhood, particularly as expressed during play, are seen as antecedents and preparations for adult sex differences. Because evolved mechanisms were adaptive to ancestral environments, they are not always adaptive for contemporary people, and this mismatch of evolved mechanisms with modern environments is seen in children’s maladjustment to some aspects of formal schooling. We argue that an evolutionary perspective can be valuable for developing a better understanding of human ontogeny in contemporary society and that a developmental perspective is important for a better understanding of evolutionary psychology.

Imitation requires the imitator to solve the correspondence problem- to translate visual information from modelled action into matching motor output. It has been widely accepted for some 30 years that the correspondence problem is solved by a specialised, innate cognitive mechanism. This is the conclusion of a poverty of the stimulus argument, realised in the active intermodal matching model of imitation, which assumes that human neonates can imitate a range of body movements. An alternative, wealth of the stimulus argument, embodied in the associative sequence learning model of imitation, proposes that the correspondence problem is solved by sensorimotor learning, and that the experience necessary for this kind of learning is provided by the sociocultural environment during human development. In a detailed and wide-ranging review of research on imitation and imitation-relevant behavior in infancy and beyond, we find substantially more evidence in favour of the wealth argument than of the poverty argument.

We presented a new learning approach to the application of service robots, which is based on learning by imitation. Service robots need to increase their set of actions, which would lead to the ability of adapting their behaviours. In contrast with traditional learning approaches learning by imitation presents considerable advantages; equip robots with the abilities to be efficient in applications requiring human interaction. The paper offers our experiences with the first stage of our approach. Experimental results show the feasibility of such an approach.

Imitation enables the individuals to acquire new abilities, and encourages social interaction and cultural transfer. The capability to obtain new abilities by observation represents many important advantages. Although imitation intends to equip robots with social skills, most of the approaches so far only focus on the development of a mechanism to imitate, and other issues that contribute to the whole process of imitation are usually ignored. This paper presents the major elements that are embedded in the process of imitation, and aims to offer a complete framework to address imitation. Experimental results at the first stage with the framework are presented, as well as results using attention process into the perception process.

The purpose of this paper is to advance the interdisciplinary dialogue commenced