Robot Storytelling Companion.
Personal Robots Group's study of
robot learning companions for
interaction design / robotics / field work
MIT MEDIA LAB, 2016-2017
TEAM: personal robots group
Can social robots collaboratively exchange stories with children as a peer and help improve their linguistic and storytelling skills?
Tega uses machine learning algorithms to learn actions that improve children's storytelling and keep them engaged. This work explores how Tega can personalize its interaction with each child over multiple encounters, because every child learns and engages differently. In Spring 2017, Tega survived a three-month deployment in six classrooms in the Boston area, pioneering the field of long-term human-robot interaction.
Social robot learning companions hold great promise for augmenting the efforts of parents and teachers to promote learning, academic knowledge and the wellbeing of children. Social robots can physically, socially, and emotionally play and engage with children in the real world. They can be designed to interact with children in a collaborative, peer-like way during playful educational activities. The interactions between a child and a robot resemble the speech acts between children and adults or peers, and offer a unique opportunity to personalize social interactions to promote areas of development important for learning to read and academic success. When a child enters Kindergarten, she is a unique distribution of the various cognitive, visual, social and linguistic skills needed to be a successful reader. However, in at-risk communities, it is almost impossible for a Kindergarten teacher to offer a curriculum that addresses the diverse cognitive and pre-literacy starting points upon which children enter school. Young children would clearly benefit from personalized instruction that can measure and adapt to many intersecting domains of skills and abilities during the process of learning to read and storytell.
As part of this long-term deployment in classrooms, storytelling interactions were designed accompanied by questions to gage the child's understanding. Affect and natural language inputs were used to facilitate the interaction. This project was led by Cynthia Breazeal and Hae Won Park, with members of the group assisting in the process and conducting field work with children.
- conducted field work over several months with young kids in elementary schools
- prototyping of story interaction components using a state machine
Python | user research | ROS