The development of numerical cognition in children and artificial systems: a review of the current knowledge and proposals for multi-disciplinary research

Numerical cognition is a distinctive component of human intelligence such that the observation of its practice provides a window into high-level brain function. The modelling of numerical abilities in artificial cognitive systems can help to confirm existing child development hypotheses and define new ones by means of computational simulations. Meanwhile, new research will help to discover innovative principles for the design of artificial agents with advanced reasoning capabilities and clarify the underlying algorithms (e.g. deep learning) that can be highly effective but difficult to understand for humans. This article promotes new investigation by providing a common resource for researchers with different backgrounds, including computer science, robotics, neuroscience, psychology, and education, who are interested in pursuing scientific collaboration on mutually stimulating research on this topic. The article emphasises the fundamental role of embodiment in the initial development of numerical cognition in children. This strong relationship with the body motivates the Cognitive Developmental Robotics (CDR) approach for new research that can (among others) help to standardise data collection and provide open databases for benchmarking computational models. Furthermore, we discuss the potential application of robots in classrooms and argue that the CDR approach can be extended to assist educators and favour mathematical education.