Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques
Mobile robots use simultaneous localization and mapping (SLAM) techniques for generating maps of unknown environments through navigating its. In this work, firstly SLAM technique was considered based on extended Kalman filter (EKF) which it was implemented and evaluated at unknown environments with...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Al-Nahrain Journal for Engineering Sciences
2025-07-01
|
| Series: | مجلة النهرين للعلوم الهندسية |
| Subjects: | |
| Online Access: | https://nahje.com/index.php/main/article/view/1139 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850066258448351232 |
|---|---|
| author | Sarah H. Abdulridha Dheyaa J. Kadhim |
| author_facet | Sarah H. Abdulridha Dheyaa J. Kadhim |
| author_sort | Sarah H. Abdulridha |
| collection | DOAJ |
| description |
Mobile robots use simultaneous localization and mapping (SLAM) techniques for generating maps of unknown environments through navigating its. In this work, firstly SLAM technique was considered based on extended Kalman filter (EKF) which it was implemented and evaluated at unknown environments with different number of landmarks to estimate mobile robot’s position and build a map for navigated environment at the same time. Then, the detectable landmarks will play an important role in controlling the overall navigation process as well EKF-SLAM technique’s performance. After that, three intelligent optimization algorithms are proposed to enhance the performance of the EKF-SLAM trajectory for the mobile robot, these algorithms are: particle swarm optimization (PSO), chaotic particle swarm optimization (CPSO) and genetic optimization (GA). MATLAB simulation results show that CPSO algorithm outperforms PSO and GA algorithms in terms of minimizing the mean square error (MSE1) with increasing the number of landmarks, where MSE1 is the mean square error of EKF-SLAM according to the actual trajectory. The simulation results show also the performance of EKF-SLAM trajectory is better than the performance of the Odometry trajectory and becomes best with using intelligent optimization algorithms.
|
| format | Article |
| id | doaj-art-01d5db61cab04a0da82d0d3bb6982dae |
| institution | DOAJ |
| issn | 2521-9154 2521-9162 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Al-Nahrain Journal for Engineering Sciences |
| record_format | Article |
| series | مجلة النهرين للعلوم الهندسية |
| spelling | doaj-art-01d5db61cab04a0da82d0d3bb6982dae2025-08-20T02:48:49ZengAl-Nahrain Journal for Engineering Sciencesمجلة النهرين للعلوم الهندسية2521-91542521-91622025-07-0128210.29194/NJES.28020164Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization TechniquesSarah H. Abdulridha0Dheyaa J. Kadhim1Dept. of Computer Eng., Al-Nahrain University, Baghdad, Iraq.Dept. of Electrical Engineering, University of Baghdad, Baghdad-Iraq. Mobile robots use simultaneous localization and mapping (SLAM) techniques for generating maps of unknown environments through navigating its. In this work, firstly SLAM technique was considered based on extended Kalman filter (EKF) which it was implemented and evaluated at unknown environments with different number of landmarks to estimate mobile robot’s position and build a map for navigated environment at the same time. Then, the detectable landmarks will play an important role in controlling the overall navigation process as well EKF-SLAM technique’s performance. After that, three intelligent optimization algorithms are proposed to enhance the performance of the EKF-SLAM trajectory for the mobile robot, these algorithms are: particle swarm optimization (PSO), chaotic particle swarm optimization (CPSO) and genetic optimization (GA). MATLAB simulation results show that CPSO algorithm outperforms PSO and GA algorithms in terms of minimizing the mean square error (MSE1) with increasing the number of landmarks, where MSE1 is the mean square error of EKF-SLAM according to the actual trajectory. The simulation results show also the performance of EKF-SLAM trajectory is better than the performance of the Odometry trajectory and becomes best with using intelligent optimization algorithms. https://nahje.com/index.php/main/article/view/1139Mobile RobotEKF-SLAMPSOGACPSO |
| spellingShingle | Sarah H. Abdulridha Dheyaa J. Kadhim Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques مجلة النهرين للعلوم الهندسية Mobile Robot EKF-SLAM PSO GA CPSO |
| title | Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques |
| title_full | Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques |
| title_fullStr | Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques |
| title_full_unstemmed | Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques |
| title_short | Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques |
| title_sort | optimal mobile robot navigation in unknown environments using different optimization techniques |
| topic | Mobile Robot EKF-SLAM PSO GA CPSO |
| url | https://nahje.com/index.php/main/article/view/1139 |
| work_keys_str_mv | AT sarahhabdulridha optimalmobilerobotnavigationinunknownenvironmentsusingdifferentoptimizationtechniques AT dheyaajkadhim optimalmobilerobotnavigationinunknownenvironmentsusingdifferentoptimizationtechniques |