Dynamic path planning using a modified genetic algorithm
Genetic algorithm (GA) is well-known algorithm to find a feasible path planning which can be defined as global optimum problem. The drawback of GA is the high computation due to random process on each operator. In this research, the new initial population integrating with new crossover operator str...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2024-08-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | https://ijain.org/index.php/IJAIN/article/view/699 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850102061276856320 |
|---|---|
| author | Awang Hendrianto Pratomo Oyas Wahyunggoro Hendri Himawan Triharminto |
| author_facet | Awang Hendrianto Pratomo Oyas Wahyunggoro Hendri Himawan Triharminto |
| author_sort | Awang Hendrianto Pratomo |
| collection | DOAJ |
| description | Genetic algorithm (GA) is well-known algorithm to find a feasible path planning which can be defined as global optimum problem. The drawback of GA is the high computation due to random process on each operator. In this research, the new initial population integrating with new crossover operator strategy was proposed. The parameter is the length of distance travelled of the robot. Before employing the crossover operator, generating a c-obstacle have been done. The c-obstacle is used as a filter to reduce unnecessary nodes to decrease time computation. After that, the initial population has been determined. The initial population is divided into two parents which parent’s chromosome contains an initial and goal position. The second parents are fulfilled with nodes from each obstacle. The genes of chromosome will add with c-obstacle nodes. Crossover operator is applied after filtering and c-obstacle of possible hopping is determined. Filtering method is used to remove unnecessary nodes that are part of c-obstacle. Fitness function considers the distance from the last to next position. Optimum value is the shortest distance of path planning which avoids the obstacle in front. The aim of the proposed method is to reduce the random population and random operating in GA. By using a similar data set of previous researches, the modified GA can reduce the total of generation and yield an adaptive generation number. This means that the modified GA converges faster than the other GA methods. |
| format | Article |
| id | doaj-art-760ca33c19d8483b95bf4c1b14ad86d4 |
| institution | DOAJ |
| issn | 2442-6571 2548-3161 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj-art-760ca33c19d8483b95bf4c1b14ad86d42025-08-20T02:39:51ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612024-08-0110339740910.26555/ijain.v10i3.699292Dynamic path planning using a modified genetic algorithmAwang Hendrianto Pratomo0Oyas Wahyunggoro1Hendri Himawan Triharminto2Department of Electrical Engineering and Informastion Technology, Engineering Faculty, Universitas Gadjah MadaDepartment of Informatics Engineering, Faculty of Industrial Engineering, Universitas Pembangunan Nasional “Veteran” YogyakartaDepartment of Informatics Engineering, Faculty of Industrial Engineering, Universitas Pembangunan Nasional “Veteran” YogyakartaGenetic algorithm (GA) is well-known algorithm to find a feasible path planning which can be defined as global optimum problem. The drawback of GA is the high computation due to random process on each operator. In this research, the new initial population integrating with new crossover operator strategy was proposed. The parameter is the length of distance travelled of the robot. Before employing the crossover operator, generating a c-obstacle have been done. The c-obstacle is used as a filter to reduce unnecessary nodes to decrease time computation. After that, the initial population has been determined. The initial population is divided into two parents which parent’s chromosome contains an initial and goal position. The second parents are fulfilled with nodes from each obstacle. The genes of chromosome will add with c-obstacle nodes. Crossover operator is applied after filtering and c-obstacle of possible hopping is determined. Filtering method is used to remove unnecessary nodes that are part of c-obstacle. Fitness function considers the distance from the last to next position. Optimum value is the shortest distance of path planning which avoids the obstacle in front. The aim of the proposed method is to reduce the random population and random operating in GA. By using a similar data set of previous researches, the modified GA can reduce the total of generation and yield an adaptive generation number. This means that the modified GA converges faster than the other GA methods.https://ijain.org/index.php/IJAIN/article/view/699path planninggenetic algorithminitial populationc-obstaclecrossover operator |
| spellingShingle | Awang Hendrianto Pratomo Oyas Wahyunggoro Hendri Himawan Triharminto Dynamic path planning using a modified genetic algorithm IJAIN (International Journal of Advances in Intelligent Informatics) path planning genetic algorithm initial population c-obstacle crossover operator |
| title | Dynamic path planning using a modified genetic algorithm |
| title_full | Dynamic path planning using a modified genetic algorithm |
| title_fullStr | Dynamic path planning using a modified genetic algorithm |
| title_full_unstemmed | Dynamic path planning using a modified genetic algorithm |
| title_short | Dynamic path planning using a modified genetic algorithm |
| title_sort | dynamic path planning using a modified genetic algorithm |
| topic | path planning genetic algorithm initial population c-obstacle crossover operator |
| url | https://ijain.org/index.php/IJAIN/article/view/699 |
| work_keys_str_mv | AT awanghendriantopratomo dynamicpathplanningusingamodifiedgeneticalgorithm AT oyaswahyunggoro dynamicpathplanningusingamodifiedgeneticalgorithm AT hendrihimawantriharminto dynamicpathplanningusingamodifiedgeneticalgorithm |