Date of Award

10-18-2019

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Dan Wu

Keywords

Grid path planning, IGA, Path planning

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

Path Planning of mobile robots is one of the essential tasks in robotic research and studies with intelligent technologies. It helps in determining the path from a source to the destination. It has extended its roots from classic approaches to further improvements over time, such as evolutionary approaches. Ant Colony Optimization (ACO) and Genetic algorithm are well known evolutionary approaches in effective path planning. This research work focuses on the Max-Min Ant System (MMAS) derived from the ACO evolutionary approach of Ant System (AS) and Improved Genetic Algorithm (IGA) which is efficient over the classical Genetic Algorithm. In-order to study robot path planning two methods are combined in this research work combining MMAS and IGA as two-hybrid methods MMAS-IGA and IGA-MMAS . The results of the two-hybrid methods will be deriving the near optimal solution, demonstrated in the experimental study of this work. Grid maps are used for simulating the robot path planning environment which is modeled using the grid method. Genetic operators of IGA are combined with MMAS for the enhancement of the overall result of the methods IGA-MMAS and MMAS-IGA. The effectiveness of these two methods will be determined in the simulation modeled using MATLAB environment. The experimental results of these methods are done in a static environment and the results of MMAS-IGA and IGA-MMAS are compared to the path planning method GA-ACO.

Share

COinS