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

Uncertainty and Efficiency in Adaptive Robot Learning and Control.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Uncertainty and Efficiency in Adaptive Robot Learning and Control./
作者:	Harrison, James Michael.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	174 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-06, Section: B.
Contained By:	Dissertations Abstracts International83-06B.
標題:	Confidence intervals. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28827986
ISBN:	9798494461629

Uncertainty and Efficiency in Adaptive Robot Learning and Control.
Harrison, James Michael.

Uncertainty and Efficiency in Adaptive Robot Learning and Control. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 174 p.

Source: Dissertations Abstracts International, Volume: 83-06, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

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

Autonomous robots have the potential to free humans from dangerous or dull work. To achieve truly autonomous operation, robots must be able to understand unstructured environments and make safe decisions in the face of uncertainty and non-stationarity. As such, robots must be able to learn about, and react to, changing operating conditions or environments continuously, efficiently, and safely. While the last decade has seen rapid advances in the capabilities of machine learning systems driven by deep learning, these systems are limited in their ability to adapt online, learn with small amounts of data, and characterize uncertainty. The desiderata of learning robots therefore directly conflict with the weaknesses of modern deep learning systems. This thesis aims to remedy this conflict and develop robot learning systems that are capable of learning safely and efficiently.In the first part of the thesis we develop tools for efficient learning in changing environments. In particular, we develop tools for the meta-learning problem setting---in which data from a collection of environments may be used to accelerate learning in a new environment---in both the regression and classification setting. These algorithms are based on exact Bayesian inference on meta-learned features. This approach enables characterization of uncertainty in the face of small amounts of within-environment data, and efficient learning via exact conditioning. We extend these approaches to time-varying settings beyond episodic variation, including continuous gradual environmental variation and sharp, changepoint-like variation.In the second part of the thesis we adapt these tools to the problem of robot modeling and control. In particular, we investigate the problem of combining our neural network-based meta-learning models with prior knowledge in the form of a nominal dynamics model, and discuss design decisions to yield better performance and parameter identification. We then develop a strategy for safe learning control. This strategy combines methods from modern constrained control---in particular, robust model predictive control---with ideas from classical adaptive control to yield a computationally efficient, simple to implement, and guaranteed safe control strategy capable of learning online. We conclude the thesis with a discussion of short, intermediate, and long-term next steps in extending the ideas developed herein toward the goal of true robot autonomy.

ISBN: 9798494461629Subjects--Topical Terms:

566017
Confidence intervals.
Subjects--Index Terms:

Uncertainty

Uncertainty and Efficiency in Adaptive Robot Learning and Control.
LDR:03697nmm a2200397 4500 001 2348090
005 20220906075203.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798494461629
035 $a (MiAaPQ)AAI28827986
035 $a (MiAaPQ)STANFORDhh754jn1534
035 $a AAI28827986
040 $a MiAaPQ $c MiAaPQ
100 1 $a Harrison, James Michael. $3 3687409
245 1 0 $a Uncertainty and Efficiency in Adaptive Robot Learning and Control.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 174 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-06, Section: B.
500 $a Advisor: Pavone, Marco;Okamura, Allison.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Autonomous robots have the potential to free humans from dangerous or dull work. To achieve truly autonomous operation, robots must be able to understand unstructured environments and make safe decisions in the face of uncertainty and non-stationarity. As such, robots must be able to learn about, and react to, changing operating conditions or environments continuously, efficiently, and safely. While the last decade has seen rapid advances in the capabilities of machine learning systems driven by deep learning, these systems are limited in their ability to adapt online, learn with small amounts of data, and characterize uncertainty. The desiderata of learning robots therefore directly conflict with the weaknesses of modern deep learning systems. This thesis aims to remedy this conflict and develop robot learning systems that are capable of learning safely and efficiently.In the first part of the thesis we develop tools for efficient learning in changing environments. In particular, we develop tools for the meta-learning problem setting---in which data from a collection of environments may be used to accelerate learning in a new environment---in both the regression and classification setting. These algorithms are based on exact Bayesian inference on meta-learned features. This approach enables characterization of uncertainty in the face of small amounts of within-environment data, and efficient learning via exact conditioning. We extend these approaches to time-varying settings beyond episodic variation, including continuous gradual environmental variation and sharp, changepoint-like variation.In the second part of the thesis we adapt these tools to the problem of robot modeling and control. In particular, we investigate the problem of combining our neural network-based meta-learning models with prior knowledge in the form of a nominal dynamics model, and discuss design decisions to yield better performance and parameter identification. We then develop a strategy for safe learning control. This strategy combines methods from modern constrained control---in particular, robust model predictive control---with ideas from classical adaptive control to yield a computationally efficient, simple to implement, and guaranteed safe control strategy capable of learning online. We conclude the thesis with a discussion of short, intermediate, and long-term next steps in extending the ideas developed herein toward the goal of true robot autonomy.
590 $a School code: 0212.
650 4 $a Confidence intervals. $3 566017
650 4 $a Parameter identification. $3 3687410
650 4 $a Applied mathematics. $3 2122814
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Robotics. $3 519753
653 $a Uncertainty
653 $a Efficiency
653 $a Adaptive robot learning
653 $a Robot control
653 $a Autonomous robots
690 $a 0984
690 $a 0800
690 $a 0364
690 $a 0771
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-06B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28827986