A Simulated Environment for Long-term Interactions

Autor(es)

Azevedo, Helio ; Souza, Isaque Elcio ; Colombini, EL ; Junior, PLJD ; Garcia, LTD ; Goncalves, LMG ; Sa, STD ; Estrada, EDD ; Botelho, SSD

• Tipo de documento: Artigo Científico
• Fonte: 2019 LATIN AMERICAN ROBOTICS SYMPOSIUM, 2019 BRAZILIAN SYMPOSIUM ON ROBOTICS (SBR) AND 2019 WORKSHOP ON ROBOTICS IN EDUCATION (LARS-SBR-WRE 2019); v. N/A, p. 6-pg., 2019-01-01.

Resumo

Long-term interaction with social robots represents a subarea of HumanRobot Interaction (HRI) that studies how patterns of interaction between users and social robots evolve over time. The interest in this subject results from the need of modern society to develop social robots that can engage and support users for long periods of time. A large portion of the population should benefit from this kind of research as for example, people with physical or intellectual disability. This paper presents an evolution of the architecture called Cognitive Model Development Environment (CMDE) to meet the requirements of applications involving long-term interaction. The proposed evolution includes three features. The first one develops the concept of Memory in OntPercept ontology to represent memory information records. The idea is to explore the versatility offered by relationship representation in ontologies. The second feature introduces Forgetting abstraction that allows the control of memory volume using reasoning tools also inherent to ontologies. Third, evolve the Robot House Simulator (RHS) by including new human avatars to represent different ages and behaviors. (AU)

• Processo FAPESP: 14/50851-0 - INCT 2014: Instituto Nacional de Ciência e Tecnologia para Sistemas Autônomos Cooperativos Aplicados em Segurança e Meio Ambiente
• Beneficiário: Marco Henrique Terra
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/01687-0 - Arquitetura e aplicações para robótica em ambientes inteligentes
• Beneficiário: Roseli Aparecida Francelin Romero
• Modalidade de apoio: Auxílio à Pesquisa - Regular