Evidence of an Emergent "Self" in Continual Robot Learning

Abstract

A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a &#34;self&#34;, and if so how to differentiate the &#34;self&#34; from other cognitive structures. We propose that the &#34;self&#34; can be isolated by seeking the invariant portion of cognitive process that changes relatively little compared to more rapidly acquired cognitive skills - because our self is the most persistent aspect of our experiences. We used this principle to analyze the cognitive structure of robots under two conditions: One robot learns a constant task, while a second undergoes continual learning under variable tasks. We find that robots subjected to continual learning develop an invariant subnetwork that is significantly more stable (p < 0.001) compared to the control, and that this subnetwork is also functionally important: preserving it aids adaptation while damaging it impairs performance. We validate this pattern across three different robots spanning locomotion and manipulation.