A comparative study on ant-colony algorithm and genetic algorithm for mobile robot planning.
This paper investigates the optimization of routing for robotics vehicles in automated warehouses in Malaysia. Focusing on routing optimization, the study evaluates Ant-Colony Optimization (ACO) and Genetic Algorithm (GA) in Mobile Robot Planning. Key challenges includes efficient routing among tas...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/11966/1/A%20comparative%20study%20on%20ant-colony%20algorithm%20and%20genetic%20algorithm%20for%20mobile%20robot%20planning.pdf http://eprints.uthm.edu.my/11966/ https://doi.org/10.1007/978-3-031-66965-1_28 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper investigates the optimization of routing for robotics vehicles in automated warehouses in Malaysia. Focusing on routing optimization, the study evaluates Ant-Colony Optimization (ACO) and Genetic Algorithm (GA)
in Mobile Robot Planning. Key challenges includes efficient routing among task scheduling, and path planning complexities. Objectives include analyzing features
of mobile robot planning and representing them in ACO and GA, implementation ACO and GA algorithms for solving routing problems using dataset, and evaluating their performance. The research anticipates significant contributions
to algorithmic solutions, utilizing Python-based experiments aligned with Software Engineering practice, providing practical insights for routing optimization in automated warehouses. Results indicates that ACO outperforms GA in minimizing travel distance, establishing it as the superior routing algorithm for both case studies. Case study 1, the ACO algorithm achieved a best distance of 1036 (u) with execution time 1.67 (s), while the GA algorithm resulted in a best distance 1062 (u) with execution time 0.08 (s). For case study 2, the ACO algorithm achieved a best distance of 1071 (u) with execution time 1.91 (s), while the GA algorithm resulted in a best distance of 1082 (u) with execution time 0.08 (s). Multiple code
execution cycles are conducted to provide average findings, ensuring the strength and consistency of the assessment. In conclusion, the study successfully identifies key features in warehouses routing, implements ACO and GA algorithms, and
evaluates the performance based on achieved routes and distance. |
|---|