Performance comparison between genetic algorithm and ant colony optimization algorithm for mobile robot path planning in global static environment / Nohaidda Sariff
Path planning (PP) together with mapping and localization are important elements in autonomous mobile robot navigation systems. In both global and local PP systems, a mobile robot should be able to navigate effectively until it reaches a destination without colliding with any obstacles within an env...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/15462/1/TM_NOHAIDDA%20SARIFF%20EE%2011_5.PDF |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Path planning (PP) together with mapping and localization are important elements in autonomous mobile robot navigation systems. In both global and local PP systems, a mobile robot should be able to navigate effectively until it reaches a destination without colliding with any obstacles within an environment. Due to the importance of global path planning in mobile robot navigation systems, the research presented herewith focused on the optimization problem of path planning for mobile robots. The problem is to find the global path that satisfies the optimization criteria, which are shorter path length and less computation time. This will lead to the reduction of the energy consumption of the robot itself. The main goal of this research is to compare the performances between Genetic Algorithm (GA) and Ant Colony Optimization (ACO) algorithm. The objective is to verify and compare the effectiveness of both algorithms in finding the optimal robot path in different types of global map environments. The selected environments consist of different complexities of feasible nodes and different complexities of obstacles. In the initial stage, the test environments were constructed. Subsequently, both algorithms were applied to the test environments. Finally, the performances of both algorithms were analyzed and evaluated based on the required criteria. The results of the research indicated that ACO was more robust compared to GA as it was capable of finding the optimal path in all the tested environments. In addition, parameter settings of ACO required for each case were very straightforward compared to GA. The robustness of ACO to determine an optimal path was proven in this research. This indicates that ACO optimization technique has great potential for solving other optimization problems. |
|---|