A robot that counts like a child: a developmental model of counting and pointing

TL;DR

This paper presents a neuro-robotics model that enables a humanoid robot to count objects and point to them, exploring how embodiment influences numerical cognition, with results comparable to human child development.

Contribution

Introduces a novel neuro-robotics model combining neural networks and embodiment to study counting and pointing, bridging robotics and developmental cognition research.

Findings

Robot successfully counts and points to objects.

Counting performance parallels human child development.

Impact of set size and distance on counting accuracy was analyzed.

Abstract

In this paper, a novel neuro-robotics model capable of counting real items is introduced. The model allows us to investigate the interaction between embodiment and numerical cognition. This is composed of a deep neural network capable of image processing and sequential tasks performance, and a robotic platform providing the embodiment - the iCub humanoid robot. The network is trained using images from the robot's cameras and proprioceptive signals from its joints. The trained model is able to count a set of items and at the same time points to them. We investigate the influence of pointing on the counting process and compare our results with those from studies with children. Several training approaches are presented in this paper all of them uses pre-training routine allowing the network to gain the ability of pointing and number recitation (from 1 to 10) prior to counting training. The impact of the counted set size and distance to the objects are investigated. The obtained results on counting performance show similarities with those from human studies.