Meaningful agents: a semiotic approach

Meaning is a key problem in intelligent systems design. Most approaches in literature still adopt naive definitions, which cause them many subtle problems such as the symbol grounding problem. In this work we propose a semiotic approach to this problem based on the triadic model of sign developed by C.S. Peirce. In order to observe the key aspects of this model of simulated semiosis (meaning processes) we developed an experimental protocol inspired on the work of Luc Steels (the talking heads experiment). We argue that, with the proposed theory, meaning emerges within each agent without any external interference (from other agents or the creature designer himself); they can exhibit semiosis, in a simulated form.