Iolanda Leite’s research lies at the intersection of Human-Robot Interaction and Artificial Intelligence. She takes inspiration from human theories of emotion and social relations to develop computational models that support the dynamics of social interactions between people and machines. These models rely on novel algorithms and machine learning techniques that allow robots to adapt their behavior to the particular context, user needs and preferences over time. Her long-term goal is to build autonomous social robots that can capture, learn from and respond appropriately to the subtle dynamics of real-world situations, allowing for truly useful and efficient long-term interactions with people.
My plans for the fellowship period
The main research question I plan to address is whether role-playing activities with socially assistive robots can be used to promote cultural awareness in young children. Role-playing offers a safe space for children to practice hypothetical social situations before encountering similar situations in the real world with their peers. Here, robots offer an inexpensive and reliable alternative to human actors, displaying controlled and personalized behavior across interventions with different trainees. Moreover, a robot’s appearance and behavior can be parameterized to tailor the learning goals of each child, and previous research has shown that because of the physical presence, higher learning gains can be achieved with robots when compared to the same content being delivered by other technologies such as virtual characters on a screen. The target age group is 7-11-year-olds because at this stage children are capable of taking the perspective of others and acknowledging that not everyone shares the same ways of thinking.
How will my work change children’s and youth’s lives?
Children grow up in an increasingly diverse and multicultural world. The development of assistive robotic technologies that can educate about different cultural perspectives and foster a sense of social responsibility in children is beneficial for inclusive learning environments. The outcomes of my work can have a positive impact both on children who recently moved to a new country and on native children. Along with the societal impact, this work will contribute with novel algorithms to enable social robots to adapt interactions to the needs of each individual child, allowing for truly effective and engaging learning sessions. This will enable robots to be deployed autonomously in schools for periods of weeks and months, contrasting with existing solutions that only support a limited number of interactions with the same child and require permanent developer supervision. The novel computational algorithms developed in the project will inform the next generation of socially assistive robots for children in application domains such as education and health-care.