A comparison of three evolved controllers used for robotic navigation
This paper compares three evolved controllers including, an evolvable hardware controller, an artificial neural network and a lookup table. The comparison made between these controllers looks at relative evolutionary efficiency, controller performance and scalability. The controllers were evolved fo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2020-12-01
|
| Series: | AIMS Electronics and Electrical Engineering |
| Subjects: | |
| Online Access: | http://www.aimspress.com/article/10.3934/ElectrEng.2020.3.259?viewType=HTML |
| _version_ | 1831648999467122688 |
|---|---|
| author | Mark Beckerleg Justin Matulich Philip Wong |
| author_facet | Mark Beckerleg Justin Matulich Philip Wong |
| author_sort | Mark Beckerleg |
| collection | DOAJ |
| description | This paper compares three evolved controllers including, an evolvable hardware controller, an artificial neural network and a lookup table. The comparison made between these controllers looks at relative evolutionary efficiency, controller performance and scalability. The controllers were evolved for three navigational behaviours including light following, obstacle avoidance, and the combined behaviours of light following while avoiding obstacles. Both monolithic and subsumption techniques were used to evolve the combined behaviours to evaluate scalability. It was found that all three evolved controllers performed the assigned tasks equally well. The evolutionary efficiency and scalability of the evolvable hardware and artificial neural network were similar, whereas the lookup table had an acceptable result but was subjective to scalability. The virtual-FPGA can be implemented in a fault tolerant system using a hybrid FGPAs with a hard-core processor for continuous evolution. |
| first_indexed | 2024-12-19T14:42:26Z |
| format | Article |
| id | doaj.art-bcd7f45f875d40389942a3f5c5ac147a |
| institution | Directory Open Access Journal |
| issn | 2578-1588 |
| language | English |
| last_indexed | 2024-12-19T14:42:26Z |
| publishDate | 2020-12-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Electronics and Electrical Engineering |
| spelling | doaj.art-bcd7f45f875d40389942a3f5c5ac147a2022-12-21T20:17:03ZengAIMS PressAIMS Electronics and Electrical Engineering2578-15882020-12-014325928610.3934/ElectrEng.2020.3.259A comparison of three evolved controllers used for robotic navigationMark Beckerleg0Justin Matulich1Philip Wong2Department of Electrical and Electronic Engineering, Auckland University of Technology, Auckland, New ZealandDepartment of Electrical and Electronic Engineering, Auckland University of Technology, Auckland, New ZealandDepartment of Electrical and Electronic Engineering, Auckland University of Technology, Auckland, New ZealandThis paper compares three evolved controllers including, an evolvable hardware controller, an artificial neural network and a lookup table. The comparison made between these controllers looks at relative evolutionary efficiency, controller performance and scalability. The controllers were evolved for three navigational behaviours including light following, obstacle avoidance, and the combined behaviours of light following while avoiding obstacles. Both monolithic and subsumption techniques were used to evolve the combined behaviours to evaluate scalability. It was found that all three evolved controllers performed the assigned tasks equally well. The evolutionary efficiency and scalability of the evolvable hardware and artificial neural network were similar, whereas the lookup table had an acceptable result but was subjective to scalability. The virtual-FPGA can be implemented in a fault tolerant system using a hybrid FGPAs with a hard-core processor for continuous evolution.http://www.aimspress.com/article/10.3934/ElectrEng.2020.3.259?viewType=HTMLevolutionary robotsartificial neural networkevolvable hardwarelookup tablelight followingobstacle avoidancegenetic algorithms |
| spellingShingle | Mark Beckerleg Justin Matulich Philip Wong A comparison of three evolved controllers used for robotic navigation AIMS Electronics and Electrical Engineering evolutionary robots artificial neural network evolvable hardware lookup table light following obstacle avoidance genetic algorithms |
| title | A comparison of three evolved controllers used for robotic navigation |
| title_full | A comparison of three evolved controllers used for robotic navigation |
| title_fullStr | A comparison of three evolved controllers used for robotic navigation |
| title_full_unstemmed | A comparison of three evolved controllers used for robotic navigation |
| title_short | A comparison of three evolved controllers used for robotic navigation |
| title_sort | comparison of three evolved controllers used for robotic navigation |
| topic | evolutionary robots artificial neural network evolvable hardware lookup table light following obstacle avoidance genetic algorithms |
| url | http://www.aimspress.com/article/10.3934/ElectrEng.2020.3.259?viewType=HTML |
| work_keys_str_mv | AT markbeckerleg acomparisonofthreeevolvedcontrollersusedforroboticnavigation AT justinmatulich acomparisonofthreeevolvedcontrollersusedforroboticnavigation AT philipwong acomparisonofthreeevolvedcontrollersusedforroboticnavigation AT markbeckerleg comparisonofthreeevolvedcontrollersusedforroboticnavigation AT justinmatulich comparisonofthreeevolvedcontrollersusedforroboticnavigation AT philipwong comparisonofthreeevolvedcontrollersusedforroboticnavigation |