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

Improving Scalability of Evolutionar...

Bernatskiy, Anton.

Linked to FindBook

Google Book

Amazon

博客來

Improving Scalability of Evolutionary Robotics with Reformulation.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Improving Scalability of Evolutionary Robotics with Reformulation./
Author:	Bernatskiy, Anton.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
Description:	200 p.
Notes:	Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B.
Contained By:	Dissertation Abstracts International80-02B(E).
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10935306
ISBN:	9780438487901

Improving Scalability of Evolutionary Robotics with Reformulation.
Bernatskiy, Anton.

Improving Scalability of Evolutionary Robotics with Reformulation. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 200 p.

Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B.

Thesis (Ph.D.)--The University of Vermont and State Agricultural College, 2018.

Creating systems that can operate autonomously in complex environments is a challenge for contemporary engineering techniques. Automatic design methods offer a promising alternative, but so far they have not been able to produce agents that outperform manual designs. One such method is evolutionary robotics. It has been shown to be a robust and versatile tool for designing robots to perform simple tasks, but more challenging tasks at present remain out of reach of the method.

ISBN: 9780438487901Subjects--Topical Terms:

523869
Computer science.

Improving Scalability of Evolutionary Robotics with Reformulation.
LDR:02481nmm a2200349 4500 001 2203248
005 20190528072654.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9780438487901
035 $a (MiAaPQ)AAI10935306
035 $a (MiAaPQ)uvm:10751
035 $a AAI10935306
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bernatskiy, Anton. $3 3430042
245 1 0 $a Improving Scalability of Evolutionary Robotics with Reformulation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 200 p.
500 $a Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B.
500 $a Adviser: Joshua C. Bongard.
502 $a Thesis (Ph.D.)--The University of Vermont and State Agricultural College, 2018.
520 $a Creating systems that can operate autonomously in complex environments is a challenge for contemporary engineering techniques. Automatic design methods offer a promising alternative, but so far they have not been able to produce agents that outperform manual designs. One such method is evolutionary robotics. It has been shown to be a robust and versatile tool for designing robots to perform simple tasks, but more challenging tasks at present remain out of reach of the method.
520 $a In this thesis I discuss and attack some problems underlying the scalability issues associated with the method. I present a new technique for evolving modular networks. I show that the performance of modularity-biased evolution depends heavily on the morphology of the robot's body and present a new method for co-evolving morphology and modular control.
520 $a To be able to reason about the new technique I develop reformulation framework: a general way to describe and reason about metaoptimization approaches. Within this framework I describe a new heuristic for developing metaoptimization approaches that is based on the technique for co-evolving morphology and modularity. I validate the framework by applying it to a practical task of zero-g autonomous assembly of structures with a fleet of small robots.
520 $a Although this work focuses on the evolutionary robotics, methods and approaches developed within it can be applied to optimization problems in any domain.
590 $a School code: 0243.
650 4 $a Computer science. $3 523869
650 4 $a Evolution & development. $3 3172418
650 4 $a Robotics. $3 519753
690 $a 0984
690 $a 0412
690 $a 0771
710 2 $a The University of Vermont and State Agricultural College. $b Computer Science. $3 3172620
773 0 $t Dissertation Abstracts International $g 80-02B(E).
790 $a 0243
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10935306