Adaptive Learning Application of the MDB Evolutionary Cognitive Architecture in Physical Agents

摘要

This work is concerned with the study of the application of the MDB (Multilevel Darwinist Brain) evolution based Cognitive Architecture in real robots performing adaptive learning tasks. The experiments described here display the capabilities of this architecture when dealing with tasks that involve real time learning from a teacher and real time adaptation to changes in the goals provided or the communication pattern used by the teacher. One of the consequences of the interaction of the robot with the environment through the MDB is the generation of induced behaviors that allow the robot to continue its operation when no teacher is present. The experiments were carried out using a Sony AIBO robot and a Pioneer 2 robot with the same mechanism running on both just to demonstrate the robustness of the approach.