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

FindBook

Google Book

Amazon

博客來

Understanding and Learning Robotic Manipulation Skills From Humans.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Understanding and Learning Robotic Manipulation Skills From Humans./
作者:	Herrero, Elena Galbally.
面頁冊數:	1 online resource (137 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
Contained By:	Dissertations Abstracts International84-05B.
標題:	Robots. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29755682click for full text (PQDT)
ISBN:	9798357505514

Understanding and Learning Robotic Manipulation Skills From Humans.
Herrero, Elena Galbally.

Understanding and Learning Robotic Manipulation Skills From Humans. - 1 online resource (137 pages)

Source: Dissertations Abstracts International, Volume: 84-05, Section: B.

Thesis (Ph.D.)--Stanford University, 2022.

Includes bibliographical references

Humans are constantly learning new skills and improving upon their existing abilities. In particular, when it comes to manipulating objects, humans are extremely effective at generalizing to new scenarios and using physical compliance to our advantage. Compliance is key to generating robust behaviors by reducing the need to rely on precise trajectories. Programming robots through predefined trajectories has been highly successful for performing tasks in structured environments, such as assembly lines. However, such an approach is not viable for real-time operations in real-world scenarios.Inspired by humans, we propose to program robots at a higher level of abstraction by using primitives that leverage contact information and compliant strategies. Compliance increases robustness to uncertainty in the environment and primitives provide us with atomic actions that can be reused to avoid coding new tasks from scratch. We have developed a framework that allows us to: (i) collect and segment human data from multiple contact-rich tasks through direct or haptic demonstrations, (ii) analyze this data and extract the human's compliant strategy, and (iii) encode the strategy into robot primitives using task-level controllers. During autonomous task execution, haptic interfaces enable human real-time intervention and additional data collection for recovery from failures.At the core of this framework is the notion of a compliant frame - an origin and three directions in space along and about which we control motion and compliance. The compliant frame is attached to the object being manipulated and together with the desired task parameters defines a primitive. Task parameters include desired forces, moments, positions, and orientations. This task specification provides a physically meaningful, low-dimensional, and robot-independent representation.This thesis presents a novel framework for learning manipulation skills from demonstration data. Leveraging compliant frames enables us to understand human actions and extract strategies that generalize across objects and robots. The framework was extensively validated through simulation and hardware experiments, including five real-world construction tasks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798357505514Subjects--Topical Terms:

529507
Robots.
Index Terms--Genre/Form:

542853
Electronic books.

Understanding and Learning Robotic Manipulation Skills From Humans.
LDR:03427nmm a2200325K 4500 001 2354656
005 20230428105640.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798357505514
035 $a (MiAaPQ)AAI29755682
035 $a (MiAaPQ)STANFORDnn835sb3161
035 $a AAI29755682
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Herrero, Elena Galbally. $3 3695015
245 1 0 $a Understanding and Learning Robotic Manipulation Skills From Humans.
264 0 $c 2022
300 $a 1 online resource (137 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
500 $a Advisor: Okamura, Allison.
502 $a Thesis (Ph.D.)--Stanford University, 2022.
504 $a Includes bibliographical references
520 $a Humans are constantly learning new skills and improving upon their existing abilities. In particular, when it comes to manipulating objects, humans are extremely effective at generalizing to new scenarios and using physical compliance to our advantage. Compliance is key to generating robust behaviors by reducing the need to rely on precise trajectories. Programming robots through predefined trajectories has been highly successful for performing tasks in structured environments, such as assembly lines. However, such an approach is not viable for real-time operations in real-world scenarios.Inspired by humans, we propose to program robots at a higher level of abstraction by using primitives that leverage contact information and compliant strategies. Compliance increases robustness to uncertainty in the environment and primitives provide us with atomic actions that can be reused to avoid coding new tasks from scratch. We have developed a framework that allows us to: (i) collect and segment human data from multiple contact-rich tasks through direct or haptic demonstrations, (ii) analyze this data and extract the human's compliant strategy, and (iii) encode the strategy into robot primitives using task-level controllers. During autonomous task execution, haptic interfaces enable human real-time intervention and additional data collection for recovery from failures.At the core of this framework is the notion of a compliant frame - an origin and three directions in space along and about which we control motion and compliance. The compliant frame is attached to the object being manipulated and together with the desired task parameters defines a primitive. Task parameters include desired forces, moments, positions, and orientations. This task specification provides a physically meaningful, low-dimensional, and robot-independent representation.This thesis presents a novel framework for learning manipulation skills from demonstration data. Leveraging compliant frames enables us to understand human actions and extract strategies that generalize across objects and robots. The framework was extensively validated through simulation and hardware experiments, including five real-world construction tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Robots. $3 529507
650 4 $a Ablation. $3 3562462
650 4 $a Onsite. $3 3690306
650 4 $a Robotics. $3 519753
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0771
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 84-05B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29755682 $z click for full text (PQDT)