Indeed, as opposed to the work in classical artificial intelligence in which engineers impose pre-defined anthropocentric tasks to robots, the techniques we develop endow the robots with the capacity of deciding by themselves which are the activities that are maximally fitted to their current capabilities. Our developmental robots autonomously and actively choose their learning situations, thus beginning by simple ones and progressively increasing their complexity. No tasks are pre-specified to the robots, which are only provided with an internal abstract reward function. For example, in the case of the Intelligent Adaptive Curiosity which we developped, this internal reward function pushes the robot to search for situations where its learning progress is maximal.

A new robot can recognize the difference between a mirror image of itself and another robot that looks just like it.

This so-called mirror image cognition is based on artificial nerve cell groups built into the robot’s computer brain that give it the ability to recognize itself and acknowledge others.