Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments

The autonomous navigation of a Mobile Robot (MR) in unknown environments populated by abundance of static and dynamic obstacles with a moving target have tremendous importance in real time applications. The ability of an MR to navigate safely, smoothly, and quickly in such environment is cruci...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohammed, Ahmed Hassan
Format:	Thesis
Language:	English
Published:	2017
Subjects:	Robots - Control Mobile robots
Online Access:	http://psasir.upm.edu.my/id/eprint/68583/1/FK%202018%2040%20-%20IR.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-upm-ir.68583
record_format	uketd_dc
spelling	my-upm-ir.685832019-05-21T03:01:01Z Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments 2017-10 Mohammed, Ahmed Hassan The autonomous navigation of a Mobile Robot (MR) in unknown environments populated by abundance of static and dynamic obstacles with a moving target have tremendous importance in real time applications. The ability of an MR to navigate safely, smoothly, and quickly in such environment is crucial. Current researches are focused on investigating these complex features in static or point-to-point dynamic environments. On the other hand, the salient downside of Q-Learning such as curse of dimensionality (CoD) is aggravated in complex environments. The objectives of this thesis is to address the issue of Adaptive Reinforcement Learning (RL) approaches in order to meet the requirements of MR navigation. Moreover, it aims to tackle CoD problem of Q-Learning (QL) to be suitable for complex applications. For this purpose, two genetic network programming with RL (GNP-RL) designs are proposed. The first design is based on obstacle target correlation (OTC) environment representation and called OTC-GNP-RL. This provides a perception of the current environment states. The second design is based on the proposed collision prediction (CP) environment representation and called CPGNP- RL. This representation is designed to provide collision prediction between MR and an obstacle, as well as the perception of current surrounded environment. Besides, it could represent an environment with compact state space and requires ones to measure positions only. Furthermore, the combination of CP and QL (CPQL) can overcome the downside of the CoD problem and improve navigation features.A simulation is used for evaluating the performance of the proposed approaches. The results show that the superiority of the proposed approaches in terms of the features of MR navigation, where all these features are taken under the design consideration of each proposed approach. Through the evaluation, CPQL, CP-GNP-RL, and OTCGNP- RL provide significant improvements in terms of safety (7.917%), smooth path (71.776%), and speed (10.89%), respectively, compared with two state-of-arts approaches, i.e. OTC based Q-learning and artificial potential field. In addition, the learning analysis of CPQL shows its efficiency and superiority in terms of learning convergence and safe navigation. Hence, the proposed approaches prove their authenticity and suitability for navigation in complex and dynamic environments. Robots - Control Mobile robots 2017-10 Thesis http://psasir.upm.edu.my/id/eprint/68583/ http://psasir.upm.edu.my/id/eprint/68583/1/FK%202018%2040%20-%20IR.pdf text en public doctoral Universiti Putra Malaysia Robots - Control Mobile robots
institution	Universiti Putra Malaysia
collection	PSAS Institutional Repository
language	English
topic	Robots - Control Mobile robots
spellingShingle	Robots - Control Mobile robots Mohammed, Ahmed Hassan Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
description	The autonomous navigation of a Mobile Robot (MR) in unknown environments populated by abundance of static and dynamic obstacles with a moving target have tremendous importance in real time applications. The ability of an MR to navigate safely, smoothly, and quickly in such environment is crucial. Current researches are focused on investigating these complex features in static or point-to-point dynamic environments. On the other hand, the salient downside of Q-Learning such as curse of dimensionality (CoD) is aggravated in complex environments. The objectives of this thesis is to address the issue of Adaptive Reinforcement Learning (RL) approaches in order to meet the requirements of MR navigation. Moreover, it aims to tackle CoD problem of Q-Learning (QL) to be suitable for complex applications. For this purpose, two genetic network programming with RL (GNP-RL) designs are proposed. The first design is based on obstacle target correlation (OTC) environment representation and called OTC-GNP-RL. This provides a perception of the current environment states. The second design is based on the proposed collision prediction (CP) environment representation and called CPGNP- RL. This representation is designed to provide collision prediction between MR and an obstacle, as well as the perception of current surrounded environment. Besides, it could represent an environment with compact state space and requires ones to measure positions only. Furthermore, the combination of CP and QL (CPQL) can overcome the downside of the CoD problem and improve navigation features.A simulation is used for evaluating the performance of the proposed approaches. The results show that the superiority of the proposed approaches in terms of the features of MR navigation, where all these features are taken under the design consideration of each proposed approach. Through the evaluation, CPQL, CP-GNP-RL, and OTCGNP- RL provide significant improvements in terms of safety (7.917%), smooth path (71.776%), and speed (10.89%), respectively, compared with two state-of-arts approaches, i.e. OTC based Q-learning and artificial potential field. In addition, the learning analysis of CPQL shows its efficiency and superiority in terms of learning convergence and safe navigation. Hence, the proposed approaches prove their authenticity and suitability for navigation in complex and dynamic environments.
format	Thesis
qualification_level	Doctorate
author	Mohammed, Ahmed Hassan
author_facet	Mohammed, Ahmed Hassan
author_sort	Mohammed, Ahmed Hassan
title	Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
title_short	Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
title_full	Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
title_fullStr	Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
title_full_unstemmed	Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
title_sort	collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments
granting_institution	Universiti Putra Malaysia
publishDate	2017
url	http://psasir.upm.edu.my/id/eprint/68583/1/FK%202018%2040%20-%20IR.pdf
_version_	1747812600301748224

Collision prediction- based genetic network programming -reinforcement learning for mobile robot adaptive navigation in unknown dynamic environments

Similar Items