A palm-sized robot that can hold conversations will go on sale in Japan next year, developer Toyota has announced. Kirobo Mini, who was 10cm (4in) high, had been designed to provide companionship, the company said. And it could tailor conversations to include comments about journeys based on data from its owner's vehicle. It also has childlike attributes, but a robotics expert told the BBC a robot could not be a substitute for a child. "He wobbles a bit, and this is meant to emulate a seated baby, which hasn't fully developed the skills to balance itself," Fuminori Kataoka, Kirobo Mini's chief design engineer, told the Reuters news agency.
This paper proposes an "Open Collective Robotics" research field, defined as an experimental study of the concepts and techniques that could lead to true collectivities between Humans and Robots. We discuss the kind of social aptitudes required for such robots groups and defend the notions of physical and social situatedness. We also present the MICRobES Project, which is a long-term experiment involving a group of 10 autonomous mobile robots immersed in an environment inhabited by humans. Introduction A few years ago, (Hewitt & Inman 1991) proposed the name "Open Systems" for work groups mixing human and software agents. As an analogy, we claim that a major issue in Collective Robotics in the next years will be an "Open Collective Robotics", i.e. robots groups immersed in human collectivities.
Imitation, play and dreams are as many means for the child to develop his understandingof the world and of its social rules. What if we were to have a robot we could play with? What if we could through play and daily interactions, as we do with our children, be a model for it and teach it (what?) to be humanlike? I advocate the use of natural humanlike interaction, such as imitation, speech and gestures, for developing likable, socially interactive robots. Asanexample, I present a prototype of toy robot, the Robota doll, which can engage in complex interaction with humans, involving speech, vision and touch. Robota learns the meaning of her users' speech through natural, imitation-based interactions.
Learning by imitation is a powerful form of learning. Different forms of imitation, like mimicry, copying, response facilitation, etc. have been studied extensively (Miklosi 1999). Recent research in robotics has begun to explore imitation as a means to allow complex robots, like humanoid robots, acquire new skills (Swinson & Bruemmer 2000). One of the key issues in imitation learning is the correspondence problem. This problem concerns the answer to the question: what action sequence of the imitator is similar to that of the demonstrator and how similar it is?
We discuss the importance of narrative intelligence (story-awareness, story-telling, historical grounding) in regard to an agent's transcendence of its immediate local temporal context to create a broad temporal horizon in which the experience and future of the agent can be accounted for, together with the advantage that narrative provides to sociality by making the experience of others available without the risk of having to undergo the experience for one's self. Concepts and consequences for the design of artifacts are surveyed, together with a brief description of a formal algebraic framework affording support for narrative grounding.