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
|
Text
Evolutionary_multi-objective_optimization_for_automatic_synthesis_of_artificial_neural_network_robot_controllers.pdf Download (125kB) | Preview |
Abstract
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 |
|---|---|
| Keyword: | Artificial life, Embodied cognition, Evolutionary artificial neural networks, Evolutionary multi-objective optimization, Evolutionary robotics |
| Subjects: | T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery > TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) |
| Department: | SCHOOL > School of Engineering and Information Technology |
| Depositing User: | ADMIN ADMIN |
| Date Deposited: | 14 Feb 2012 15:05 |
| Last Modified: | 16 Oct 2017 15:13 |
| URI: | https://eprints.ums.edu.my/id/eprint/3512 |
Actions (login required)
 |
View Item |