The AGINAO Self-Programming Engine

Abstract

AbstractThe AGINAO is a project to create a human-level artificial general intelligence system (HL AGI)embodied in the Aldebaran Robotics' NAO humanoid robot. The dynamical and open-endedcognitive engine of the robot is represented by an embedded and multi-threaded control program,that is self-crafted rather than hand-crafted, and is executed on a simulated Universal TuringMachine (UTM). The actual structure of the cognitive engine emerges as a result of placing therobot in a natural preschool-like environment and running a core start-up system that executesself-programming of the cognitive layer on top of the core layer. The data from the robot's sensorydevices supplies the training samples for the machine learning methods, while the commands sentto actuators enable testing hypotheses and getting a feedback. The individual self-createdsubroutines are supposed to reflect the patterns and concepts of the real world, while the overallprogram structure reflects the spatial and temporal hierarchy of the world dependencies. Thispaper focuses on the details of the self-programming approach, limiting the discussion of theapplied cognitive architecture to a necessary minimum.