Knowledge-Based Information Agent with Social Competence and Human Interaction Capabilities
(Duration 03/2015 - 02/2018 /// Funding: Horizon 2020 ICT 22-2014 Multimodal and Natural computer interaction Research & Innovation Actions (a) )
Migration is tradition in Europe. This is not free of challenges. Migrants often face problems, especially in the case of care. Often they don't speak the language and are not acquainted with the culture of the resident country. Moreover, they are not familiar with the care and health administrations of the country. Especially elder migrants are struggling with getting the right information and interacting with the administration. Besides, migrant temporary care workers face the problem of isolation, lack of professional background information and deficient communication with the cared and the supervision personnel.
The new project aims to do research on and develop technologies for a human-like socially competent and communicative agent that serves for migrants as a trusted information provision party and mediator in questions related to basic care and healthcare. Patients, elderly in need of care and care personnel are concerned.
To develop such an agent, a number of scientific and technological challenges have to be tackled. It must be ensured that the agent is capable to understand and correctly interpret the concerns of the user concerned, expressed by a combination of facial, gestural and verbal signals. Once understood and interpreted, the agent must be able to decide on the correct reaction to them. To be of maximal use to the user and have a maximal impact, the agent is to run on tablets, smartphones, PC's and laptops.
Two use cases
KRISTINA will advance the state of the art in dialogue management, multimodal (vocal, facial and gestural) communication analysis and multimodal communication. The technologies will be validated in two use cases with a representative number of migrants recruited as users from the migration circles identified as especially in need: elderly Turkish migrants and their relatives and short term Polish care giving personnel in Germany and North African migrants in Spain.
Almende will create an agent platform which supports migrants in their interaction with the virtual agent which represents authorities. It will do this especially by the recognition of gestures, by means of novel multi-scale computer vision approaches and agents that are capable of multimodal coordination.
Universitat Pompeu Fabra, Spain;
Centre for Research and Technology Hellas, Greece;
University of Augsburg, Germany;
Vocapia Research, France;
Uni Tübingen, Germany;
Universität Ulm, Germany;
Sociedad Española de Medicina de Familia y Comunitaria, Spain.