Evolutionary multi-objective optimization for automatic synthesis of artificial neural network robot controllers

Teo, Jason Tze Wi (2005) Evolutionary multi-objective optimization for automatic synthesis of artificial neural network robot controllers. Malaysian Journal of Computer Science, 18 (2). pp. 54-62. ISSN 0127-9084


Download (125kB) | Preview


This paper investigates the use of a multi-objective approach for evolving artificial neural networks that act as controllers for the legged locomotion of a quadrupedal robot simulated in a 3-dimensional, physics-based environment. The Pareto-frontier Differential Evolution (PDE) algorithm is used to generate a Pareto optimal set of artificial neural networks that optimize the conflicting objectives of maximizing locomotion behavior and minimizing neural network complexity. In this study, insights are provided on how the controller generates the emergent walking behavior in the creature by analyzing the evolved artificial neural networks in operation. A comparison between Pareto optimal controllers showed that ANNs with varying numbers of hidden units resulted in noticeably different locomotion behaviors. It was also found that a much higher level of sensory-motor coordination was present in the best evolved controller.

Item Type: Article
Uncontrolled Keywords: Artificial life, Embodied cognition, Evolutionary artificial neural networks, Evolutionary multi-objective optimization, Evolutionary robotics
Subjects: ?? TJ210.2-211.47 ??
Divisions: SCHOOL > School of Engineering and Information Technology
Depositing User: Unnamed user with email storage.bpmlib@ums.edu.my
Date Deposited: 14 Feb 2012 07:05
Last Modified: 16 Oct 2017 07:13
URI: http://eprints.ums.edu.my/id/eprint/3512

Actions (login required)

View Item View Item

Browse Repository
   UMS News
Quick Search

   Latest Repository

Link to other Malaysia University Institutional Repository

Malaysia University Institutional Repository