Development of a Bioinspired optimization algorithm for the automatic generation of multiple distinct behaviors in simulated mobile robots

Hanafi Ahmad Hijazi, and Patricia Anthony, (2006) Development of a Bioinspired optimization algorithm for the automatic generation of multiple distinct behaviors in simulated mobile robots. (Unpublished)

[img] Text
Development of a Bioinspired optimization algorithm for the automatic generation of multiple distinct behaviors in simulated mobile robots.pdf

Download (87kB)

Abstract

This research explores a new approach of using a multi-objective evolutionary algorithm (MOEA) to evolve robot controllers in performing phototaxis tasks while avoiding obstacles in a simulated 30 physics environment, to overcome problems involving more than one objective, where these objectives usually trade-off among each other and are expressed in different units. Experiments were conducted within a 10% noise environment with different task environment complexities to investigate whether the MOEA is effective for controller synthesis. A simulated Khepera robot is evolved by a Pareto-frontier Differential Evolution (POE) algorithm, and learned through a 3-layer feed-forward artificial neural network, attempting to simultaneously fulfill two conflicting objectives of maximizing robot phototaxis behavior while minimizing the neural network's hidden neurons by generating a Pareto optimal set of controllers. Results showed that robot controllers could be successfully developed using the POE-MOEA algorithm. The generated robot controllers allowed the robots to move towards to the light source even the simulation and testing environments are noticeably different.

Item Type: Research Report
Uncontrolled Keywords: Algorithm , simulation , robots
Subjects: Q Science > QA Mathematics
Depositing User: Noraini
Date Deposited: 01 Aug 2019 00:22
Last Modified: 01 Aug 2019 00:22
URI: http://eprints.ums.edu.my/id/eprint/23190

Actions (login required)

View Item View Item