Search for: All records

In early motor interventions from clinical rehabilitation to physical activity encouragement, one major challenge is maintaining child engagement and motivation. Robots show unique promise for addressing this challenge, but providing robots with new types of autonomous functionality is vital for promoting robot integration and usefulness in the clinic and home spaces. To provide needed autonomy capabilities for GoBot, our assistive robot for child–robot motion interventions, we propose a behavior tree framework. Within our framework, we build two trees: one manually designed based on expert knowledge of the child–robot interaction domain, and a second automatically synthesized and requiring minimal human input and time to construct. We tested each behavior tree withN= 11 children who interacted with GoBot during two behavior tree phases and a stationary-robot control phase. Our results show that both behavior tree phases tended to yield more child motion and significantly higher parent perception of child engagement, compared to the control phase. We showed that GoBot, equipped with our framework, has the potential to encourage movement and interaction in children and that a synthesized tree can be competitive with a manually designed tree. The products of this work can benefit researchers of behavior trees and child–robot interaction.