Toward sociable robots
Introduction
Recent commercial applications are emerging where the ability to interact with people in an entertaining, engaging, or anthropomorphic manner is an important part of the robot’s functionality. A new generation of robotic toys have emerged (such as Tiger Electronic’s hamsters-like Furby or Sony’s robotic dog, Aibo) whose behavior changes the more children play with it. Video games, such as Creatures, allow the participant to “genetically” design graphical critters and then interact with them. Lego Mindstorms takes a more engineering approach, providing people with a robot toolkit.
Although the ability of these products to interact with people (and people’s ability to interact with them) is limited, they are motivating the development of increasingly life-like and socially sophisticated robots. Mediated communication through robotic avatars (http://www.tele-actor.com/original.htm) would allow one to have a physical and social presence to others despite being geographically distant. Location based entertainment applications such as museum tour guide robots [13] offer not only entertainment value but also provide visitors with information of interest. Health-related applications are being explored, such as robot nursemaids that help the elderly (http://www-2.cs.cmu.edu/∼nursebot), or robotic pets (such as Omron’s NeCoRo) that are intended to provide some of the health-related benefits of pet ownership. NASAs humanoid robot, Robonaut, developed at the Johnson Space Center is envisioned to be an astronaut’s assistant. The success of these robots hinges not only on their utility but also on their ability to be responsive to and interact with people in a natural and intuitive manner.
Section snippets
Paradigms of social robots
It is important to recognize that humans are a profoundly social species. Our social-emotional intelligence is a useful and powerful means for understanding the behavior of, and for interacting with, some of the most complex entities in our world—people and other living creatures [12]. Faced with non-living things of sufficient complexity (i.e., when the observable behavior is not easily understood in terms of its underlying mechanisms), we often apply a social model to explain, understand, and
Our sociable robot, Kismet
This remainder of this paper focuses on the last paradigm, robot as sociable creature. We highlight a few core attributes of sociable robots by means of a small case study—the design and evaluation of the vocal turn-taking behavior of our robot, Kismet (see Fig. 1). One does not use Kismet to perform a task. Instead, Kismet is designed to be a robotic creature that can interact physically, affectively, and socially with humans in order to ultimately learn from them. Accordingly, our robot is
Regulating the exchange of speaking turns
The ability to exchange turns during face-to-face interactions is the cornerstone of human style communication and instruction. The tempo and rhythm of conversational turn-taking is flexible, robust to perturbation, and mutually regulated by the interlocutors. In a teaching scenario, the ability to exchange turns allows the instructor to structure the interaction, such as providing variations upon a theme. Allowing the human to respond with immediate contingency to the robot (and vice versa)
Discussion
This case study highlights the importance of mutually regulated exchanges, expressive feedback, and readable social cues in the design of sociable robots.
Pro-actively regulate interaction. Kismet takes a pro-active role in regulating its exchanges with people so that it is neither overwhelmed nor under-stimulated—a scenario suitable for learning. It has several different mechanisms to accomplish this each intuitively tunes the person’s behavior so that it is appropriate for the robot. Two of
Conclusion
Taking this body of work as a whole, we argue that endowing a robot with social skills and capabilities has benefits far beyond the interface value for the person who interacts with it. The ability for robots to interact with people and to leverage from these interactions to perform tasks better, to promote their self-maintenance, and to learn in an environment as complex as that of humans is of tremendous pragmatic and functional importance for the robot. The performance and the benefits that
Acknowledgements
The development of Kismet was funded by NTT and DARPA contract DABT 63-99-1-0012. The author would like to give special thanks to Sherry Turkle of MIT’s Science, Technology, and Society Department for our many useful and enjoyable conversations regarding human relationships with interactive technologies. Medial Lab consortium funds (from the Things that Think and Digital Life consortia) support the author’s current research interests.
Cynthia Breazeal directs the Robotic Presence Group at the MIT Media Lab. She has developed numerous autonomous robots, from planetary micro-rovers, to upper-torso humanoid robots, to highly expressive robotic faces. Always inspired by the behavior of living systems, scientific models and theories as well as artistic insights factor heavily into the hardware and software design of her robotic creations. Her current interests focus on social interaction and socially situated learning between
References (16)
- et al.
An affective mobile educator with a full-time job
Artificial Intelligence
(1999) - C. Atkeson, S. Schaal, Robot learning from demonstration, in: Proceedings of the International Conference on Machine...
The role of emotion in believable characters
Communications of the ACM
(1994)- et al.
Grounding communication in autonomous robots: an experimental study
Robotics and Autonomous Systems
(1998) - V. Braitenberg, Vehicles: Experiments in Synthetic Psychology, MIT Press, Cambridge, MA,...
- C. Breazeal, A motivational system for regulating human–robot interaction, in: Proceedings of the 15th National...
- C. Breazeal, Designing Sociable Robots, MIT Press, Cambridge, MA,...
- C. Breazeal, Emotion and sociable humanoid robots, International Journal of Human Computer Interaction, in...
Cited by (0)
Cynthia Breazeal directs the Robotic Presence Group at the MIT Media Lab. She has developed numerous autonomous robots, from planetary micro-rovers, to upper-torso humanoid robots, to highly expressive robotic faces. Always inspired by the behavior of living systems, scientific models and theories as well as artistic insights factor heavily into the hardware and software design of her robotic creations. Her current interests focus on social interaction and socially situated learning between people and life-like robots. Her graduate and postdoctoral research was carried out at the MIT Artificial Intelligence Lab. She received her Sc.D. and S.M. degrees from MIT in the Department of Electrical Engineering and Computer Science with specialization in robotics and artificial intelligence, and a BS in electrical and computer engineering from UC Santa Barbara.