Material Detail

ALIZ-E - Adaptive Strategies for Sustainable Long-Term Social Interaction

ALIZ-E - Adaptive Strategies for Sustainable Long-Term Social Interaction

This video was recorded at 5th International Conference on Cognitive Systems 2012, Vienna. Social behaviour happens in the here and now but relationships depend also on the past. When we interact with others we respond to how they behave but we also bring to the interaction our social history i.e. the sum total of our previous experiences of similar situations. Researchers are very interested to understand how humans and robots can relate socially but to date most of the work that carried out focuses on minute-by-minute interactive behaviour. The aim of the ALIZ-E project is to explore how human-robot interactions can be extended from minutes to the scale of days thus forging longer-term constructive bonds between robot and user. The ALIZ-E project will use the principles of embodied cognitive robotics to create agents capable of sustaining believable, any-depth social relationships with young users, over an extended, potentially discontinuous timeframe. The ALIZ-E project will specifically explore robot-child interaction capitalising on children's open and imaginative responses to artificial 'creatures'. Promising future applications include the development of educational companion robots for child users. The ALIZ-E project will innovate in taking robots out of the lab and putting them to the test in a health education role, with young diabetic patients, in a busy paediatric department at the Ospedale San Raffaele in Milan. One central scientific goal of ALIZ-E involves implementing memory systems to enable robots to engage in self-sustaining interactions. This requires that they should have the capacity to store and recall experiences, to learn from them and to adapt their social behaviour on the basis of their previous experiences. A distributed, "switch board" model, in which memory provides the substrate through which other cognitive modalities interact, will be used to provide socially coherent, long-term patterns of behaviour. The robots will learn online through unstructured interactions in dynamic environments and number of different machine learning approaches will be integrated to facilitate this functionality. Cloud computing techniques will be used to provide off-board computing resources for robots interacting autonomously. Real world social interaction hinges on making appropriate responses to the behaviour of others thus another key aspect of ALIZ-E concerns understanding emotion in human–robot interaction. For a robot to sustain a social relationship with a child, it must be able to interpret the emotional and affective content of the interaction and be able to produce behaviour signalling appropriate affective responses back to the child. Non-verbal behaviour will play an important part in the robots' social repertoire but in order to engage the user fully the robots will require the capacity to understand and to produce speech. Verbal and non-verbal behaviour will necessarily be tightly coupled with learning and memory to support the longer-term functioning of a social bond between robot and child. ALIZ-E will use Aldebaran Nao robots as an implementation platform, the Nao is a small, autonomous, humanoid robot already widely used in robot soccer. The project, coordinated by Dr. Tony Belpaeme at the University of Plymouth, involves a consortium of 7 academic partners comprising The University of Plymouth, Vrije Universiteit Brussel (Belgium), Deutsches Forschungzentrum für Küustliche Intelligenz (Germany), Imperial College (UK), The University of Hertfordshire (UK), National Research Council - Padova (Italy) and The Netherlands Organization for Applied Scientific Research (The Netherlands) plus commercial partners GOSTAI (France) and Fondazione Centro San Raffaele del Monte Tabor (Italy). Funded under the European Commission 7th Framework Programme the ALIZ-E project began in April 2010 and will run for a total of 4.5 years.


  • Editor Reviews
  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.