Social Robot Toolkit

The goal of the role of the social robot toolkit is to provide a platform for children to learn through playful interaction. The social robot (Soro) toolkit allows preschool children to experiment with computational concepts while teaching a social robot new rules. The toolkit also provides a platform for learning interpersonal skills through the use of storytelling that integrates interpersonal and computational concepts. Soro harnesses preschoolers’ natural interest in social interaction to familiarize them with new concepts.

The programming interface is composed of colorful reusable vinyl stickers. The children are taught how to create rules that will make the robot do new things. The children show new rules to the robot, while the experimenter teleoperates the rules on a tablet, allowing the children to later interact with the robot and test the new rule.

The toolkit is grounded in rule-based programming and concepts from behavioral programming. It allows exploring computational concepts such as sequences, event-triggers, non-determinism, etc. The sensing part is tele-operated, to allow rapid prototyping. The toolkit can be used for both outreach and education, teaching about programming and about how robots work.

Preliminary experiments with 4-8 year old children show that the children love experimenting with the interface and are learning about how robots work, and about computational concepts such as sequences and order. In an experiment with preschool age children (4 and 5 year olds), 85% of the children were able to create a valid rule by themselves, learning about triggers and actions.

This research has been developed with the collaboration of Edith Ackermann, a professor of developmental psychology and with advice from Mitchel Resnick, the LEGO Papert Professor of Learning Research from the Lifelong Kindergarten group at the media lab, MIT. This research was supported by the National Science Foundation (NSF) under Grants CCF-1138986. Any opinions, findings and conclusions, or recommendations expressed in this research are those of the authors and do not represent the views of the NSF.