Print ISSN: 1811-9212

Online ISSN: 2617-3352

Keywords : Fitness Function


Enhanced Genetic Algorithm Based on Node Codes for Mobile Robot Path Planning

Dr. Mohamed Jasim Mohamed; Mrs. Farah S. Khoshaba

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2012, Volume 12, Issue 2, Pages 69-80

Abstract: In this paper, a new Enhanced Genetic Algorithm (EGA) is used to find the best global path planning for a mobile robot according to a specific criterion. The EGA is enhanced by a new encoding method, new initial population creation method, new crossover and mutation operations as well as new additional operations correction operation and classification operation. The study considers the case when the mobile robot works in a known static environment. The new proposed algorithm is built to help the mobile robot to choose the shortest path without it colliding with the obstacles allocated in a working known environment. The use of grid map in the environment helps to locate nodes on the map where all nodes are assigned by coordinate values. The start and the target nodes of the required path are given prior to the proposed algorithm. Each node represents a landmark that the mobile robot either passes through only one time or never passes through during its journey from start node to the target node. Two examples of known static mobile robot environments with many obstacles in each one are studied and the proposed algorithm is applied on them. The results show that the proposed algorithm is very reliable, accurate, efficient and fast to give the best global path planning for the two cases.

Genetic Algorithm Using Sub-path Codes for Mobile Robot Path Planning

Dr. Mohamed Jasim Mohamed

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2012, Volume 12, Issue 1, Pages 104-117

In this paper, a new method for finding global optimal path planning is
proposed using a Genetic Algorithm (GA). A map of known static environment as well
as a start node and a target node connecting an optimal path which is required to be
found are given beforehand. The chosen nodes in a known static environment are
connected by sub-paths among each other. Each path is represented by a series of subpaths
which connect the sequential nodes to form this path. Each sub-path radiating
from each node is labeled by an integer. The chromosome code of a path is a string of
series integers that represent the labels of sub-paths which are passed through traveling
from start node to target node. Two factors are integrated into a fitness function of the
proposed genetic algorithm: the feasibility of collision avoidance path and the shortest
distance of path. Two examples of known static environment maps are taken in this
study with different numbers of obstacles and nodes. Simulation results show the
effectiveness and feasibility of the proposed GA using sub-path codes to find optimum
path planning for mobile robot.