Designing Children’s New Learning Partner: Collaborative Artificial Intelligence for Learning to Solve the Rubik’s Cube
Forest Agostinelli, Mihir Mavalankar, Vedant Khandelwal, Hengtao Tang, Dezhi Wu, Barnett Berry, Biplav Srivastava, Amit Sheth, Matthew J. Irvin
Abstract
Developing the problem solving skills of children is a challenging problem that is crucial for the future of our society. Given that artificial intelligence (AI) has been used to solve problems across a wide variety of domains, AI offers unique opportunities to develop problem solving skills using a multitude of tasks that pique the curiosity of children. To make this a reality, it is necessary to address the uninterpretable “black-box” that AI often appears to be. Towards this goal, we design a collaborative artificial intelligence algorithm that uses a human-in-the-loop approach to allow students to discover their own personalized solutions to problems. This collaborative algorithm builds on state-of-the-art AI algorithms and leverages additional interpretable structures, namely knowledge graphs and decision trees, to create a fully interpretable process that is able to explain solutions in their entirety. We describe this algorithm when applied to solving the Rubik’s cube as well as our planned user-interface and assessment methods.