Exploring generation of a genetic robot's personality through neural and evolutionary means

This paper proposes a way to generate a robot genome that contributes to defining the personality of a software robot or an artificial life in a mobile phone. The personality should be both complex and feature-rich, but still plausible by human standards for an emotional life form. However, it becomes increasingly difficult and time-consuming to ensure reliability, variability and consistency for the robot's personality while manually initializing values for the individual genes. To overcome this difficulty, this paper proposes a neural network algorithm for a genetic robot's personality (NNGRP) and an upgraded version of a previously introduced evolutionary algorithm for a genetic robot's personality (EAGRP). The robot genomes for heterogeneous personalities are demonstrably generated via the NNGRP and the EAGRP and compared. The implementation is embedded into genetic robots in a mobile phone to verify the feasibility and effectiveness of each algorithm.