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

Whole-body strategies for mobility a...

Deegan, Patrick.

FindBook

Google Book

Amazon

博客來

Whole-body strategies for mobility and manipulation.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Whole-body strategies for mobility and manipulation./
作者:	Deegan, Patrick.
面頁冊數:	125 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4340.
Contained By:	Dissertation Abstracts International71-07B.
標題:	Engineering, Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3409566
ISBN:	9781124072258

Whole-body strategies for mobility and manipulation.
Deegan, Patrick.

Whole-body strategies for mobility and manipulation. - 125 p.

Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4340.

Thesis (Ph.D.)--University of Massachusetts Amherst, 2010.

The robotics community has succeeded in creating remarkable machines and task-level programming tools, but arguably has failed to apply sophisticated autonomous machines to sophisticated tasks. One reason is that this combination leads to prohibitive complexity. Biological systems provide many examples of integrated systems that combine high-performance and flexibility, with logically-organized low-level control. Sophisticated organisms have evolved that depend on physical dexterity to thrive in a particular ecological niche while mitigating computational and behavioral complexity.

ISBN: 9781124072258Subjects--Topical Terms:

1018454
Engineering, Robotics.

Whole-body strategies for mobility and manipulation.
LDR:04071nam 2200361 4500 001 1405113
005 20111206130406.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124072258
035 $a (UMI)AAI3409566
035 $a AAI3409566
040 $a UMI $c UMI
100 1 $a Deegan, Patrick. $3 1684470
245 1 0 $a Whole-body strategies for mobility and manipulation.
300 $a 125 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4340.
500 $a Adviser: Roderic Grupen.
502 $a Thesis (Ph.D.)--University of Massachusetts Amherst, 2010.
520 $a The robotics community has succeeded in creating remarkable machines and task-level programming tools, but arguably has failed to apply sophisticated autonomous machines to sophisticated tasks. One reason is that this combination leads to prohibitive complexity. Biological systems provide many examples of integrated systems that combine high-performance and flexibility, with logically-organized low-level control. Sophisticated organisms have evolved that depend on physical dexterity to thrive in a particular ecological niche while mitigating computational and behavioral complexity.
520 $a This dissertation investigates the potential for a new kind of hybrid robotic design process. A design for performance that combines mechanical dexterity with low-level embedded firmware that organizes behavior and facilitates programming at a higher level. I propose that dexterous machines can incorporate embedded firmware that express the "aptitudes" implicit in the design of the robot and hierarchically organize the behavior of the system for programming. This is a win-win situation where the quality of the embedded firmware determines how efficiently programmers (autonomous learning algorithms or human programmers) can construct control programs that are robust, flexible, and respond gracefully to unanticipated circumstances.
520 $a This dissertation introduces the uBot-5---a mobile manipulator concept for human environments that provides dexterous modes for mobility and manipulation and control firmware that organizes these behavioral modes locally for use by applications code. Postural control underlies the uniform treatment of several mobility modes that engage different combinations of sensor and motor resources. The result is a platform for studying "whole-body" control strategies that can be applied jointly to simultaneous mobility and manipulation objectives.
520 $a The thesis examines the specification and development of both: (1) a dexterous robot for unstructured environments, and (2) the embedded firmware that organizes dexterous behavior for mobility and manipulation tasks. Integrated solutions are proposed that control transitions between postural "modes" and provide a logically organized dexterous behavior hierarchy. Firmware programming can also be used to construct an efficient API for user programming and autonomous machine learning.
520 $a My goal is to contribute technologies that can support new robotic applications in our culture that require fully integrated dexterous robots in unstructured environments. Personal robotics is an important emerging application that depends on seamlessly integrated and sophisticated machines, controllers, and adaptability. Logically organized representations for use in task-level application development are critical to pull this off. The impact of such technology could be significant---with applications that include healthcare and telemedicine, exploration, emergency response, logistics, and flexible manufacturing.
590 $a School code: 0118.
650 4 $a Engineering, Robotics. $3 1018454
650 4 $a Computer Science. $3 626642
690 $a 0771
690 $a 0984
710 2 $a University of Massachusetts Amherst. $b Computer Science. $3 1023848
773 0 $t Dissertation Abstracts International $g 71-07B.
790 1 0 $a Grupen, Roderic, $e advisor
790 1 0 $a Brock, Oliver $e committee member
790 1 0 $a Barto, Andrew $e committee member
790 1 0 $a Van Emmerik, Richard $e committee member
790 $a 0118
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3409566