東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Intelligent Control of Legged Soft Robot.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Intelligent Control of Legged Soft Robot./
Author:	Kaainoa, Carina Elena.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	46 p.
Notes:	Source: Masters Abstracts International, Volume: 83-02.
Contained By:	Masters Abstracts International83-02.
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494278
ISBN:	9798534663020

Intelligent Control of Legged Soft Robot.
Kaainoa, Carina Elena.

Intelligent Control of Legged Soft Robot. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 46 p.

Source: Masters Abstracts International, Volume: 83-02.

Thesis (M.S.)--California State University, Los Angeles, 2021.

This item must not be sold to any third party vendors.

Soft robots made of soft and extensible materials accomplish tasks via shape-changing by use of pneumatic or fluidic actuation. Dynamic modeling of soft robots has been challenging due to the nonlinearity and heterogeneity inherent from their soft material bodies, therefore, the model-based control methods cannot be directly applied. In this thesis, motion control of a pneumatically actuated quadrupedal soft robot via a combination of reinforcement learning and a dead-band proportional integral derivative controller is proposed. The coordinated rhythmic motion of a soft quadruped robot is governed by the Kuramoto central pattern generator which represents a continuous, smooth control policy with small number of parameters. A reinforcement learning methodology called parameter-exploring policy gradient, a gradient estimation algorithm, is utilized to find the forward motion optimal control policy. Finally, a dead-band proportional integral derivative controller is designed for trajectory control. The effectiveness of the proposed tracking control method is demonstrated via simulation.

ISBN: 9798534663020Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Dynamic modeling

Intelligent Control of Legged Soft Robot.
LDR:02348nmm a2200409 4500 001 2343196
005 20220502104158.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798534663020
035 $a (MiAaPQ)AAI28494278
035 $a AAI28494278
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kaainoa, Carina Elena. $3 3681672
245 1 0 $a Intelligent Control of Legged Soft Robot.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 46 p.
500 $a Source: Masters Abstracts International, Volume: 83-02.
500 $a Advisor: Karimlou, Kamran.
502 $a Thesis (M.S.)--California State University, Los Angeles, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Soft robots made of soft and extensible materials accomplish tasks via shape-changing by use of pneumatic or fluidic actuation. Dynamic modeling of soft robots has been challenging due to the nonlinearity and heterogeneity inherent from their soft material bodies, therefore, the model-based control methods cannot be directly applied. In this thesis, motion control of a pneumatically actuated quadrupedal soft robot via a combination of reinforcement learning and a dead-band proportional integral derivative controller is proposed. The coordinated rhythmic motion of a soft quadruped robot is governed by the Kuramoto central pattern generator which represents a continuous, smooth control policy with small number of parameters. A reinforcement learning methodology called parameter-exploring policy gradient, a gradient estimation algorithm, is utilized to find the forward motion optimal control policy. Finally, a dead-band proportional integral derivative controller is designed for trajectory control. The effectiveness of the proposed tracking control method is demonstrated via simulation.
590 $a School code: 0962.
650 4 $a Electrical engineering. $3 649834
650 4 $a Artificial intelligence. $3 516317
650 4 $a Mechanical engineering. $3 649730
650 4 $a Robotics. $3 519753
650 4 $a Control theory. $3 535880
650 4 $a Research. $3 531893
650 4 $a Standard deviation. $3 3560390
650 4 $a Normal distribution. $3 3561025
650 4 $a Optimization. $3 891104
650 4 $a Legs. $3 3563163
650 4 $a Robots. $3 529507
650 4 $a Motion control. $3 3681673
650 4 $a Probability distribution. $3 3562293
650 4 $a Generators. $3 3681674
650 4 $a Simulation. $3 644748
650 4 $a Controllers. $3 3559217
650 4 $a Oscillators. $3 3681675
650 4 $a Design. $3 518875
650 4 $a Probability. $3 518898
650 4 $a Methods. $3 3560391
650 4 $a Algorithms. $3 536374
650 4 $a Walking. $3 548733
653 $a Dynamic modeling
653 $a Motion control
653 $a Pneumatically actuation
653 $a Quadrupedal soft robot
653 $a Reinforcement learning
653 $a Dead-band proportional integral derivative controller
690 $a 0544
690 $a 0800
690 $a 0548
690 $a 0771
690 $a 0389
710 2 $a California State University, Los Angeles. $b Electrical and Computer Engineering. $3 3181383
773 0 $t Masters Abstracts International $g 83-02.
790 $a 0962
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494278