東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Deep Reinforcement Learning with Con...

Liu, Wenxing.

FindBook

Google Book

Amazon

博客來

Deep Reinforcement Learning with Consensus for Manipulators.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Reinforcement Learning with Consensus for Manipulators./
作者:	Liu, Wenxing.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	212 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
Contained By:	Dissertations Abstracts International85-09B.
標題:	Kinematics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30841290
ISBN:	9798381840339

Deep Reinforcement Learning with Consensus for Manipulators.
Liu, Wenxing.

Deep Reinforcement Learning with Consensus for Manipulators. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 212 p.

Source: Dissertations Abstracts International, Volume: 85-09, Section: B.

Thesis (Ph.D.)--The University of Manchester (United Kingdom), 2023.

With the development of industrialization, the working environment of robotics gradually becomes complex, diverse, and fast. Most manipulators at present are still designed for simple action repetition, which means that the working environment is determined and the target should be relatively fixed. Therefore, they lack the ability to perceive the surrounding environment. The main purpose of this thesis is to develop consensus-based training and deep reinforcement learning methods that enable robot arms to interact with the environment autonomously.First of all, a model-free off-policy actor-critic based deep reinforcement learning method is proposed to solve the classical path planning problem of a UR5 robot arm. The proposed method not only guarantees that the joint angle of the UR5 robotic arm lies within the allowable range each time when it reaches the random target point, but also ensures that the joint angle of the UR5 robotic arm is always within the allowable range during the entire episode of training.Moreover, a self-supervised vision-based deep reinforcement learning method that allows robots to pick and place objects effectively and efficiently when directly transferring a training model from simulation to the real world is demonstrated. A heightsensitive action policy is specially designed for the proposed method to deal with crowded and stacked objects in challenging environments. The training model with the proposed approach can be applied directly to a real suction task without any finetuning from the real world while maintaining a high suction success rate. It is also validated that the training model can be deployed to suction novel objects in a real experiment with a suction success rate of 90% without any real-world fine-tuning.Additionally, an algorithm that combines actor-critic based off-policy method with consensus-based distributed training is proposed to deal with multi-agent deep reinforcement learning problems. Specially, a convergence analysis of a consensus algorithm for a type of nonlinear systems with a Lyapunov method is developed, and this result is used to analyse the convergence properties of the actor and the critic training parameters. To validate the implementation of the proposed algorithm, a multi-agent training framework is proposed to train each UR5 robot arm to reach the random target position. Experiments are provided to demonstrate the effectiveness and feasibility of the proposed algorithm.Finally, a Consensus-based Sim-and-Real deep reinforcement learning algorithm is developed for manipulator pick-and-place tasks. Agents are trained in both simulators and the real environment simultaneously to get the optimal policies for both sim-and-real worlds. The proposed algorithm saves required training time and shows comparable performance in both sim-and-real worlds.

ISBN: 9798381840339Subjects--Topical Terms:

571109
Kinematics.

Deep Reinforcement Learning with Consensus for Manipulators.
LDR:04011nmm a2200373 4500 001 2401427
005 20241022112613.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798381840339
035 $a (MiAaPQ)AAI30841290
035 $a (MiAaPQ)Manchester_UK66d7b7bc-6283-4385-b1b0-520dc46ea43d
035 $a AAI30841290
035 $a 2401427
040 $a MiAaPQ $c MiAaPQ
100 1 $a Liu, Wenxing. $3 3771522
245 1 0 $a Deep Reinforcement Learning with Consensus for Manipulators.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 212 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
500 $a Advisor: Carrasco , Joaquin;Herrmann, Guido.
502 $a Thesis (Ph.D.)--The University of Manchester (United Kingdom), 2023.
520 $a With the development of industrialization, the working environment of robotics gradually becomes complex, diverse, and fast. Most manipulators at present are still designed for simple action repetition, which means that the working environment is determined and the target should be relatively fixed. Therefore, they lack the ability to perceive the surrounding environment. The main purpose of this thesis is to develop consensus-based training and deep reinforcement learning methods that enable robot arms to interact with the environment autonomously.First of all, a model-free off-policy actor-critic based deep reinforcement learning method is proposed to solve the classical path planning problem of a UR5 robot arm. The proposed method not only guarantees that the joint angle of the UR5 robotic arm lies within the allowable range each time when it reaches the random target point, but also ensures that the joint angle of the UR5 robotic arm is always within the allowable range during the entire episode of training.Moreover, a self-supervised vision-based deep reinforcement learning method that allows robots to pick and place objects effectively and efficiently when directly transferring a training model from simulation to the real world is demonstrated. A heightsensitive action policy is specially designed for the proposed method to deal with crowded and stacked objects in challenging environments. The training model with the proposed approach can be applied directly to a real suction task without any finetuning from the real world while maintaining a high suction success rate. It is also validated that the training model can be deployed to suction novel objects in a real experiment with a suction success rate of 90% without any real-world fine-tuning.Additionally, an algorithm that combines actor-critic based off-policy method with consensus-based distributed training is proposed to deal with multi-agent deep reinforcement learning problems. Specially, a convergence analysis of a consensus algorithm for a type of nonlinear systems with a Lyapunov method is developed, and this result is used to analyse the convergence properties of the actor and the critic training parameters. To validate the implementation of the proposed algorithm, a multi-agent training framework is proposed to train each UR5 robot arm to reach the random target position. Experiments are provided to demonstrate the effectiveness and feasibility of the proposed algorithm.Finally, a Consensus-based Sim-and-Real deep reinforcement learning algorithm is developed for manipulator pick-and-place tasks. Agents are trained in both simulators and the real environment simultaneously to get the optimal policies for both sim-and-real worlds. The proposed algorithm saves required training time and shows comparable performance in both sim-and-real worlds.
590 $a School code: 1543.
650 4 $a Kinematics. $3 571109
650 4 $a Deep learning. $3 3554982
650 4 $a Teaching methods. $3 595505
650 4 $a Success. $3 518195
650 4 $a Computer aided design--CAD. $3 3561162
650 4 $a Neural networks. $3 677449
650 4 $a Robots. $3 529507
650 4 $a Eigenvalues. $3 631789
650 4 $a Feedback. $3 677181
650 4 $a Robotics. $3 519753
650 4 $a Design. $3 518875
650 4 $a Pedagogy. $3 2122828
650 4 $a Education. $3 516579
690 $a 0771
690 $a 0800
690 $a 0389
690 $a 0456
690 $a 0515
710 2 $a The University of Manchester (United Kingdom). $3 3422292
773 0 $t Dissertations Abstracts International $g 85-09B.
790 $a 1543
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30841290