Open Lectures

Kerstin Dautehahn and Christopher Nehaniv will visit CRL and give open lectures on the use of robot in autism therapy and on imitation and social learning, respectivly. Anyone is welcome!

Kerstin Dautenhahn has been working on the application of robots and other technology to the remedy for autism and related communication disorders. Her talk will introduce "AuRoRa Project", in which she and her colleagues are exploring the nature of commmunication and social intelligence.

Christopher Nahaniv has been working on evolution in biological and robotics systems. He is going to give us a lecture on imitation and social learning in life and in robots.

Kerstin Dautenhahn and Christopher Nehaniv are the editors of "Imitation in Animals and Artifacts" (MIT Press, 2002). Kerstin Dautenhahn is one of the editors of "Socially Intelligent Agents: Creating relationships with computers and robots" (Kluwer, 2002).


 2003年7月22日に University of Hertfordshire, UK の Kerstin Dautenhahn さんと Christopher Nehaniv さんの講演会を開催することになりま した。皆様のご参加をお待ちしております。

 Kerstin Dautenhahn さんの講演は,自閉症の療育にロボットを利用するとい うユニークな試み(AuRoRa Project)の背景・現状・展望に関するものです.社 会的知能やコミュニケーションの本質に,自閉症療育をとおして迫ります.

 Christopher Nehaniv さんの講演は,動物およびロボットにおける模倣と社会 的学習の意味とそのメカニズムに関するものです.7/16にCIRA2003(神戸)で行 うチュートリアルのダイジェスト版です.

 Kerstin Dautenhahn さんと Christopher Nehaniv さんは,"Imitation in Animals and Artifacts" (MIT Press, 2002) を編集しています.また,Kerstin Dautenhahn さんは "Socially Intelligent Agents: Creating relationships with computers and robots" (Kluwer, 2002) の第一編集者でもあります.

Dr. Kerstin Dautenhahn
Professor of Artificial Intelligence,
Adaptive Systems Research Group, University of Hertfordshire, UK

The Aurora Project: Interactive Robots in Autism Therapy
(joint work with members of the Aurora project team)

The Aurora project systematically investigates the usage of robots in autism therapy ( Particularly, we study whether and how interaction skills can be taught to autistic children. So far we have been using two types of robots: mobile robots and a small humanoid robotic doll [Dautenhahn, Billard 2002]. The different robots facilitate different types of interactions. Our general set up of the trials is very playful, the children are not required to solve any tasks other than playing, and the only purpose of the robot is to engage children with autism in therapeutically, or educationally relevant behaviours such as turn-taking and imitation. A key issue is that the children proactively initiate interactions rather than merely respond to particular stimuli. The chosen set up is social, i.e. it involves not only the robot and the autistic child present, but can include other children, the teacher or other adults. This social scenario is used by some children in a very constructive manner demonstrating their communicative competence [Dautenhahn et al 2002]. In our work we analysed different types of interactions that we observed in a series of trials where children with autism played with the robots, including trials with pairs of children [Dautenhahn & Werry, 2002; Werry et al 2001]. In a comparative study we studied how autistic children interact with a mobile robot as opposed to a non-robotic toy. Our findings include evidence that the children paid more attention, and directed more eye gaze towards the robot.

Our current work addresses a) long-term studies on the therapeutic benefits of robots in autism therapy, as well as b) how to design robots that can adapt to interaction styles and preferences of individual children.

T. Salter, R. te Boekhorst, K. Dautenhahn, D. Jacob (2003) Using Infrared Sensors for Identifying Robot-Human Interaction Styles: A Case Study. Proc. TIMR 2003, Bristol UK.

K. Dautenhahn, I. Werry (2002) A Quantitative Technique for Analysing Robot-Human Interactions. Proc. IROS2002, Lausanne, 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1132-1138, IEEE Press.

K. Dautenhahn, I. Werry, J. Rae, P. Dickerson, P. Stribling, B. Ogden (2002) Robotic Playmates: Analysing Interactive Competencies of Children with Autism Playing with a Mobile Robot. In: K Dautenhahn, A Bond, L Ca?amero, B Edmonds (eds.): Socially Intelligent Agents - Creating Relationships with Computers and Robots, Kluwer Academic Publishers, pp. 117-124.

K. Dautenhahn, A. Billard (2002): Games Children with Autism Can Play With Robota, a Humanoid Robotic Doll. In: S. Keates and P. M. Langdon and P.J. Clarkson and P. Robinson (eds.): Universal Access and Assistive Technology, Springer-Verlag London, pp. 179-190.

Dr. Christopher L. Nehaniv
Professor of Mathematical and Evolutionary Computer Science,
University of Hertfordshire, UK

Solving the Correspondence Problem in Robotic Imitation across Embodiments:
Synchrony, Perception, and Culture in Artifacts
(joint work with Aris Alissandrakis and Kerstin Dautenhahn)

Social robotics opens up the possibility of individualized social intelligence in member robots of a community, and allows us to harness not only individual learning by the individual robot, but also the acquisition of new skills by observing other members of the community (robot, human, or virtual). We describe ALICE (Action Learning for Imitation via Correspondences between Embodiments), an implemented generic mechanism for solving the *correspondence problem* between differently embodied robots. ALICE enables a robotic agent to learn a behavioral repertoire suitable to performing a task by observing a model agent, possibly having a different type of body, joints, different number of degrees of freedom, etc. Previously we demonstrated that the character of imitation achieved will depend on the granularity of subgoal matching, and on the metrics used to evaluate success. In this work, we implement ALICE for simple robotic arm agents in simulation using various metrics for evaluating success according to actions, states, or effects or weighted combinations. We examine the roles of synchronization, looseness of perceptual match, and of proprioceptive matching by a series of experiments. As a complement to the social developmental aspects suggested by developmental psychology, our results show that *synchronization* and *loose perceptual matching* also allow for faster acquisition of behavioral compentencies at low error rates.

We also discuss the use of social learning mechanisms like ALICE for transmission of skills between robots, and give the first example of transmission of a skill through a chain of robots, despite differences in embodiment of agents involved. This simple example demonstrates that by using social learning and imitation, *cultural transmission* is possible among robots, even heterogeneous groups of robots.

A. Alissandrakis, C. L. Nehaniv, & K. Dautenhahn, "Synchrony and Perception in Robotic Imitation across Embodiments", IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA'03), 2003 (in press).

A. Alissandrakis, C. L. Nehaniv, & K. Dautenhahn, "Imitating with ALICE: Learning to Imitate Corresponding Actions across Dissimilar Embodiments'', IEEE Transactions on Systems, Man, & Cybernetics, Part A, Vol. 32, No. 4, 482-496, 2002.

K. Dautenhahn and C. L. Nehaniv, editors, Imitation in Animals and Artifacts,, MIT Press, 2002. [ISBN: 0-261-0403-7]

C. L. Nehaniv & K. Dautenhahn, "The Correspondence Problem". In: Imitation in Animals and Artifacts, MIT Press, 2002.