Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Google AI Experiments [3] is a set of simple experiments that showcase innova- tive uses of AI in UX. As part of this collection, Google shared Quick Draw, where user draws simple sketches and intelligent agent tries to guess what it depicts, and Sketch- RNN interactive demo, an experience where user starts a sketch and recurrent neural network model completes it [4]. These experiences provide fun and engaging drawing activities which have potential to be used in more educational context. This report describes CoPainter - an interactive AI drawing experience which aims to provide an educational activity based on learning by teaching paradigm - the application asks the user to draw a painting of some object in cooperation with an intel- ligent agent (which can either be a robot or an abstract entity). The activity is based on Sketch-RNN model mentioned above. Main contributions of this project are porting the Sketch-RNN web app experience to Qt, which enables integration with CoWriter code- base and makes it possible to collect more data on user activities. An additional draw in turns game mode is also introduced. The activity may possibly be extended to enable it to be used in diagnosing and treating dysgraphia, which is briefly mentioned in this re- port and is aim of further research on this project.
Wulfram Gerstner, Stanislaw Andrzej Wozniak, Ana Stanojevic, Giovanni Cherubini, Angeliki Pantazi
Cédric Duchene, Nicolas Henchoz, Emily Clare Groves, Romain Simon Collaud, Andreas Sonderegger, Yoann Pierre Douillet