BehaviourGeneration​GA

A genetic mechanism for reasoning and behaviour generation

The Behaviour Generation (BG) module is an implementation of a genetic algorithm that focuses on finding the best configuration of a robot that needs to take a route decision in order to fulfil an emergency intervention task. As part of an intelligent system used for control, the proposed algorithm can run locally, on the robot's platform, or globally, if the corresponding agent is a central supervisor that assigns tasks to robots under its control.
In its definition, behaviour generation is the module that receives objectives from the reasoning module, plans from the internal knowledge base & world model (KBWM), and transmits states to KBWM and commands to the physical executors.

The robot's configuration contains parameters that define its internal model, which then the intelligent agent uses, first in the decision making process, and then to construct the behaviour. To model some internal characteristics a fuzzy model was implemented.

This package is the software companion piece to the paper "Genetic Decision Mechanism for Reasoning and Behaviour Generation in Adaptive Intelligent Agents" by Andreea Ion, Vlad Constantinescu, Monica Patrascu

BehaviourGenerationGA was implemented and tested under Matlab 7 (R2011b).
If you find BehaviourGenerationGA useful or find any bugs please let me know. Thanks for trying the algorithm!