Abstract

Swarm robotics is a research field inspired from the natural behavior of ants, bees or fish in their natural habitat. Each group display swarm behavior in different ways. For example, ants use pheromones to trace one another in order to find a nest, reach a food source or do any operation, while bees use dance moves to attract one another to the desired place. In swarm robotics, small robots attempt to mimic insect behavior. The robotic swarm group collaborate to perform a task and collectively solve a given problem. In the process, the robots use the sensors they are equipped with to move, communicate or avoid obstacles until they collectively do the desired functionality. In this thesis, we propose a modification to the Robotic Darwinian Particle Swarm Optimization (RDPSO) algorithm. In the RDPSO, robots deployed in a rescue operation, transport one object at a time to a desired safe place. In our algorithm, we simultaneously transport multiple objects to safety. We call our algorithm Multi Robotics Darwinian Particle Swarm Optimization (MRDPSO). Our algorithm is developed and implemented on a VREP simulator using ePuck robots as swarm members. We test our algorithm using two different environment sizes complete with obstacles. First implementation is for two simultaneous object transported but can be extended to more than two. We compare our new algorithm to the results of single RDPSO and found our algorithm to be 35 to 41 % faster. We also compared our results to those obtained from three selected papers that are Ghosh, Konar, and Janarthanan [1], TORABI [2], and Kube and Bonabeau [3]. The performance measures we compare to are the accuracy of transporting all objects to desired location, and the time efficiency of transporting all the objects in our new system.

Department

Computer Science & Engineering Department

Degree Name

MS in Computer Science

Graduation Date

6-1-2018

Submission Date

May 2018

First Advisor

El-Ayat, Khaled

Committee Member 1

Elkassas, Sherif

Committee Member 2

Abbas, Hazem

Extent

100 p.

Document Type

Master's Thesis

Rights

The author retains all rights with regard to copyright. The author certifies that written permission from the owner(s) of third-party copyrighted matter included in the thesis, dissertation, paper, or record of study has been obtained. The author further certifies that IRB approval has been obtained for this thesis, or that IRB approval is not necessary for this thesis. Insofar as this thesis, dissertation, paper, or record of study is an educational record as defined in the Family Educational Rights and Privacy Act (FERPA) (20 USC 1232g), the author has granted consent to disclosure of it to anyone who requests a copy.

Institutional Review Board (IRB) Approval

Not necessary for this item

Comments

I would like to express my sincere appreciation and thank my supervisor Dr. Khaled El-Ayat, for all the help he provided through out all the time I was working on my thesis under his supervision and for all the support and pushing for this work to come to existence

Download

Share

COinS