Proposal for an Approach to Artificial Consciousness Based on Self-Consciousness

Current research on artificial consciousness is focused on phenomenal consciousness and on functional consciousness. We propose to shift the focus to self-consciousness in order to open new areas of investigation. We use an existing scenario where self-consciousness is considered as the result of an evolution of representations. Application of the scenario to the possible build up of a conscious robot also introduces questions relative to emotions in robots. Areas of investigation are proposed as a continuation of this approach. Artificial Consciousness and Consciousness Current research on artificial consciousness relies on phenomenal consciousness as a reference model for human consciousness, or introduces functional consciousness to cover the functional aspects of human consciousness. We would like to propose here an alternate approach that takes self-consciousness as a reference model. Such approach can open new areas of investigation for artificial consciousness and bring new items for research on human consciousness. Self-consciousness can be defined as “the possession of the concept of the self and the ability to use this concept in thinking about oneself” (Block, 2002). It is different from phenomenal consciousness which can be understood as “experience; the phenomenally conscious aspect of a state is what it is like to be in that state” (Block, 2002). We feel that taking self-consciousness as a reference for analyzing the possibilities of an artificial consciousness can open new perspectives for robots perception, reasoning and action. Such approach can also make available a new frame for positioning artificial consciousness versus human consciousness, understanding that the relations between phenomenal consciousness and self consciousness still remain to be clarified. Self-Consciousness and the Evolution of