الفهرس | Only 14 pages are availabe for public view |
Abstract The simultaneous localization and mapping (SLAM) problem of mobile robots is identified. FastSLAM 2.0 algorithm is considered one of the most popular approaches that is used for solving SLAM problems. In this thesis, an enhanced variant of the FastSLAM 2.0 algorithm based on an enhanced differential evolution (DE) algorithm with multi-mutation strategies is developed. It improves the performance the conventional FastSLAM 2.0 algorithm and reduces the effect of particles depletion problem. A comparison has been made with other two common algorithms to evaluate the performance of the proposed algorithm in estimating the robot and landmarks positions for a SLAM problem. The results show that the proposed algorithm estimates the robot and landmark positions, for all instances taken into consideration, with higher accuracy than the other compared algorithms. |