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

Deformable Object Manipulation: Lear...

McConachie, Dale.

Linked to FindBook

Google Book

Amazon

博客來

Deformable Object Manipulation: Learning While Doing.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deformable Object Manipulation: Learning While Doing./
Author:	McConachie, Dale.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	141 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-07, Section: B.
Contained By:	Dissertations Abstracts International82-07B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28240226
ISBN:	9798684626128

Deformable Object Manipulation: Learning While Doing.
McConachie, Dale.

Deformable Object Manipulation: Learning While Doing. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 141 p.

Source: Dissertations Abstracts International, Volume: 82-07, Section: B.

Thesis (Ph.D.)--University of Michigan, 2020.

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

This dissertation is motivated by two research questions: (1) How can robots perform a broad range of useful tasks with deformable objects without a time consuming modelling or data collection phase? and (2) How can robots take advantage of information learned while manipulating deformable objects?To address the first question, I propose a framework for deformable object manipulation that interleaves planning and control, enabling complex manipulation tasks without relying on high-fidelity modeling or simulation. Each part of the framework uses a different representation of the deformable object that is well suited for the specific requirements of each component. The key idea behind these techniques is that we do not need to explicitly model and control every part of the deformable object, instead relying on the object's natural compliance in many situations. For the second question, I consider the two major components of my framework and examine what can cause failure in each. The goal then is to learn from experience gathered while performing tasks in order to avoid making the same mistake again and again. To this end I formulate the controller's task as a Multi-Armed Bandit problem, enabling the controller to choose models based on the current circumstances. For the planner, I present a method to learn when we can rely on the robot's model of the deformable object, enabling the planner to avoid generating plans that are infeasible.This framework is demonstrated in simulation with free floating grippers as well as on a 16 DoF physical robot, where reachability and dual-arm constraints make the tasks more difficult.

ISBN: 9798684626128Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deformable object manipulation

Deformable Object Manipulation: Learning While Doing.
LDR:03000nmm a2200433 4500 001 2281753
005 20210920103359.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798684626128
035 $a (MiAaPQ)AAI28240226
035 $a (MiAaPQ)umichrackham003151
035 $a AAI28240226
040 $a MiAaPQ $c MiAaPQ
100 1 $a McConachie, Dale. $3 3560461
245 1 0 $a Deformable Object Manipulation: Learning While Doing.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 141 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-07, Section: B.
500 $a Advisor: Berenson, Dmitry.
502 $a Thesis (Ph.D.)--University of Michigan, 2020.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a This dissertation is motivated by two research questions: (1) How can robots perform a broad range of useful tasks with deformable objects without a time consuming modelling or data collection phase? and (2) How can robots take advantage of information learned while manipulating deformable objects?To address the first question, I propose a framework for deformable object manipulation that interleaves planning and control, enabling complex manipulation tasks without relying on high-fidelity modeling or simulation. Each part of the framework uses a different representation of the deformable object that is well suited for the specific requirements of each component. The key idea behind these techniques is that we do not need to explicitly model and control every part of the deformable object, instead relying on the object's natural compliance in many situations. For the second question, I consider the two major components of my framework and examine what can cause failure in each. The goal then is to learn from experience gathered while performing tasks in order to avoid making the same mistake again and again. To this end I formulate the controller's task as a Multi-Armed Bandit problem, enabling the controller to choose models based on the current circumstances. For the planner, I present a method to learn when we can rely on the robot's model of the deformable object, enabling the planner to avoid generating plans that are infeasible.This framework is demonstrated in simulation with free floating grippers as well as on a 16 DoF physical robot, where reachability and dual-arm constraints make the tasks more difficult.
590 $a School code: 0127.
650 4 $a Computer science. $3 523869
650 4 $a Technical communication. $3 3172863
650 4 $a Information technology. $3 532993
650 4 $a Artificial intelligence. $3 516317
650 4 $a Mechanical engineering. $3 649730
650 4 $a Robotics. $3 519753
653 $a Deformable object manipulation
653 $a Motion planning
653 $a Machine learning
653 $a Planning and control
653 $a Deformable object modelling
690 $a 0771
690 $a 0643
690 $a 0984
690 $a 0489
690 $a 0800
690 $a 0548
710 2 $a University of Michigan. $b Robotics. $3 3546383
773 0 $t Dissertations Abstracts International $g 82-07B.
790 $a 0127
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28240226