A robot to study the development of artwork appreciation through social interactions

In this work, we present a model based on social referencing mechanisms for the artwork appreciation development. We show that trying to reach autonomous robot artwork preferences is an interesting framework for developmental robotics. Therefore, we present an application of our model in a natural environment. The museum as an experiment place, helps us to benefit from a large number of visitors with different backgrounds and personal interests, as well as provides the challenge of the learning and recognition of an important number of artefacts (heterogeneous set of objects in terms of size, culture). To overcome some limitations like the autonomy in the learning, we proposed a first model for cumulative learning using a second-order conditioning approach with very encouraging results.