REINFORCEMENT LEARNING PADA MOBILE ROBOT OMNIDIRECTIONAL

LUBIS, FIKRI AULIA PARLINDUNGAN and Nurmaini, Siti and Rendyansyah, Rendyansyah (2020) REINFORCEMENT LEARNING PADA MOBILE ROBOT OMNIDIRECTIONAL. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381520065.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011381520065_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
Preview	Text RAMA_56201_09011381520065_0002085908_0022098804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011381520065_0002085908_0022098804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381520065_0002085908_0022098804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381520065_0002085908_0022098804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381520065_0002085908_0022098804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (302kB) | Request a copy
	Text RAMA_56201_09011381520065_0002085908_0022098804_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (466kB) | Request a copy
	Text RAMA_56201_09011381520065_0002085908_0022098804_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (340kB) | Request a copy

Abstract

Mobile robots are gaining increasing attention not only as an experiment to prove "intelligence" in theory but also as an essential component of industrial and commercial automation. Four-wheeled omnidirectional mobile robot with each wheel having independent drive and seven HC-SR04 ultrasonic sensors were used in this study. Batch reinforcement learning method is used in solving the search for optimal control problems in autonomous robots. The Neural Fitted Q Itration (NFQ) algorithm is used to solve the problem of unrealistic learning sample requirements by storing and reusing tuples of previous transitions of the system in each learning iteration. As a result, in an unobstructed environment, 20 episodes of interaction with the real system, with a success rate of 91%. Then, in the corridor barrier environment, 50 episodes of interaction with the real system, with a success rate of 86.4%. And in a complex obstacle environment, 60 episodes of interaction with real systems, with a success rate of 78.8%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Learning mobile robot, Autonomous learning robot, Batch reinforcement learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Users 7506 not found.
Date Deposited:	19 Aug 2020 03:59
Last Modified:	18 Nov 2021 03:51
URI:	http://repository.unsri.ac.id/id/eprint/33343

Actions (login required)

View Item