Intelligent robotic game devices for the assessment of children could be an important tool in the early child-hood education process. At the moment the number of instruments available for especially these target groups is limited and less ecologically valid. Assessments for children are difficult to apply, time consuming, and often lead to subjective results.

In the paper we study the additive value of combining algorithms from data science and AI with robotics to assess the well-being in humans, and more specifically children. We implement a prototype of such a device combining different open-source computer vision and sound processing software. The prototype contains three distinct activities that open up a pathway towards the evaluation of capabilities of players through their performance in these activities. The performance, robustness, and reliability of the game device prototype during play are tested, highlighting the limitations of the approach and the open-source software packages used to accomplish this task.

Monitoring these capabilities in children for instance in schools is important to ensure their healthy development. With the game devices we continuously obtain large amounts of data about the players that we process to infer their capabilities.