封面图片

Towards multi robot task allocation and navigation using deep reinforcement learning

Developing algorithms for multi robot systems to reach target positions and navigate safely in the environment is an open field of research. Most systems treat Multi Robot Task Allocation (MRTA) and Multi Robot Path Planning (MRPP) as two separate steps each with its own set of algorithms in which t...

全面介绍

Saved in:
书目详细资料
Main Authors: Elfakharany, A., Yusof, R., Ismail, Z.
格式: Conference or Workshop Item
语言:English
出版: 2020
主题:
T Technology (General)
在线阅读:http://eprints.utm.my/id/eprint/93375/1/AElfakharany2019_TowardsMultiRobotTaskAllocation.pdf
http://eprints.utm.my/id/eprint/93375/
http://dx.doi.org/10.1088/1742-6596/1447/1/012045
标签: 添加标签
没有标签, 成为第一个标记此记录!
id my.utm.93375
record_format eprints
spelling my.utm.933752021-11-30T08:20:52Z http://eprints.utm.my/id/eprint/93375/ Towards multi robot task allocation and navigation using deep reinforcement learning Elfakharany, A. Yusof, R. Ismail, Z. T Technology (General) Developing algorithms for multi robot systems to reach target positions and navigate safely in the environment is an open field of research. Most systems treat Multi Robot Task Allocation (MRTA) and Multi Robot Path Planning (MRPP) as two separate steps each with its own set of algorithms in which the MRTA algorithm assigns each robot to a task and the MRPP algorithm guides each robot through the environment towards the assigned goal position while avoiding both static and dynamic obstacles. In this paper, we present a method that combines both steps by using a deep reinforcement learning model. The model consists of a decentralized sensor level policy which outputs the robot's velocity to guide it through the environment towards the selected goal position and avoiding collisions. The model was trained in a simulation environment and all the robots are homogenous differential drive robots. The objective is to ensure that each robot reaches a unique goal position with the number of goal positions is equal to the number of robots. The results of training the policy in an environment is presented with both static and dynamic obstacles with four robots and four goal positions. 2020 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/93375/1/AElfakharany2019_TowardsMultiRobotTaskAllocation.pdf Elfakharany, A. and Yusof, R. and Ismail, Z. (2020) Towards multi robot task allocation and navigation using deep reinforcement learning. In: 4th International Conference on Advanced Technology and Applied Sciences, ICaTAS 2019, 10-12 Sep 2019, Cairo, Egypt. http://dx.doi.org/10.1088/1742-6596/1447/1/012045
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Elfakharany, A.
Yusof, R.
Ismail, Z.
Towards multi robot task allocation and navigation using deep reinforcement learning
description Developing algorithms for multi robot systems to reach target positions and navigate safely in the environment is an open field of research. Most systems treat Multi Robot Task Allocation (MRTA) and Multi Robot Path Planning (MRPP) as two separate steps each with its own set of algorithms in which the MRTA algorithm assigns each robot to a task and the MRPP algorithm guides each robot through the environment towards the assigned goal position while avoiding both static and dynamic obstacles. In this paper, we present a method that combines both steps by using a deep reinforcement learning model. The model consists of a decentralized sensor level policy which outputs the robot's velocity to guide it through the environment towards the selected goal position and avoiding collisions. The model was trained in a simulation environment and all the robots are homogenous differential drive robots. The objective is to ensure that each robot reaches a unique goal position with the number of goal positions is equal to the number of robots. The results of training the policy in an environment is presented with both static and dynamic obstacles with four robots and four goal positions.
format Conference or Workshop Item
author Elfakharany, A.
Yusof, R.
Ismail, Z.
author_facet Elfakharany, A.
Yusof, R.
Ismail, Z.
author_sort Elfakharany, A.
title Towards multi robot task allocation and navigation using deep reinforcement learning
title_short Towards multi robot task allocation and navigation using deep reinforcement learning
title_full Towards multi robot task allocation and navigation using deep reinforcement learning
title_fullStr Towards multi robot task allocation and navigation using deep reinforcement learning
title_full_unstemmed Towards multi robot task allocation and navigation using deep reinforcement learning
title_sort towards multi robot task allocation and navigation using deep reinforcement learning
publishDate 2020
url http://eprints.utm.my/id/eprint/93375/1/AElfakharany2019_TowardsMultiRobotTaskAllocation.pdf
http://eprints.utm.my/id/eprint/93375/
http://dx.doi.org/10.1088/1742-6596/1447/1/012045
_version_ 1718926058912219136
score 13.251813

相似书籍