國立虎尾科技大學 |

Pretrained Representations for Embodied AI.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Pretrained Representations for Embodied AI./
Author:	Sax, Alexander.
Description:	1 online resource (159 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
Subject:	Statistics. -
Online resource:	click for full text (PQDT)
ISBN:	9798380382403

Pretrained Representations for Embodied AI.
Sax, Alexander.

Pretrained Representations for Embodied AI. - 1 online resource (159 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--University of California, Berkeley, 2023.

Includes bibliographical references

The world is messy and imperfect, unstructured and complex, and nonetheless we must still accomplish the basic behaviors necessary for survival. It is for this purpose, ecologically relevant behavior, that vision evolved 500-600 million years ago.This thesis is about how learn representations of the visual world that are useful for the types of behaviors we might want an embodied AI system to do. In the first part of this thesis, we systematically study how bottlenecking visual inputs through different pretrained representations affects the ability of a robot to learn different atomic navigation skills (Chapter 2) and manipulation skills (Chapter 3) through trial-and-error. The main finding is that the appropriate pretrained representation greatly improves the sample efficiency for skill acquisition, and greatly improves the generalization of the learned skill. In the second part of the thesis, we use the lessons learned in order to improve the accuracy of the representations in a larger variety of contexts (indoors, outdoors, tabletop settings, and so on). In Chapter 4 we do this through adding cross-prediction consistency objectives. In Chapter 5 we do this by leveraging vast amounts of 3D data available on the internet and from a robot's prior experience.The methods are primarily developed for the purpose of vision and action, but many of the ideas are general and could work for other sensory modalities and behaviors.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380382403Subjects--Topical Terms:

556824
Statistics.
Subjects--Index Terms:

Computational ethologyIndex Terms--Genre/Form:

554714
Electronic books.

Pretrained Representations for Embodied AI.
LDR:02846ntm a22004097 4500 001 1146237
005 20240812064349.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380382403
035 $a (MiAaPQ)AAI30427043
035 $a AAI30427043
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Sax, Alexander. $3 1471595
245 1 0 $a Pretrained Representations for Embodied AI.
264 0 $c 2023
300 $a 1 online resource (159 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: 85-03, Section: B.
500 $a Advisor: Malik, Jitendra;Zamir, Amir.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2023.
504 $a Includes bibliographical references
520 $a The world is messy and imperfect, unstructured and complex, and nonetheless we must still accomplish the basic behaviors necessary for survival. It is for this purpose, ecologically relevant behavior, that vision evolved 500-600 million years ago.This thesis is about how learn representations of the visual world that are useful for the types of behaviors we might want an embodied AI system to do. In the first part of this thesis, we systematically study how bottlenecking visual inputs through different pretrained representations affects the ability of a robot to learn different atomic navigation skills (Chapter 2) and manipulation skills (Chapter 3) through trial-and-error. The main finding is that the appropriate pretrained representation greatly improves the sample efficiency for skill acquisition, and greatly improves the generalization of the learned skill. In the second part of the thesis, we use the lessons learned in order to improve the accuracy of the representations in a larger variety of contexts (indoors, outdoors, tabletop settings, and so on). In Chapter 4 we do this through adding cross-prediction consistency objectives. In Chapter 5 we do this by leveraging vast amounts of 3D data available on the internet and from a robot's prior experience.The methods are primarily developed for the purpose of vision and action, but many of the ideas are general and could work for other sensory modalities and behaviors.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 556824
650 4 $a Computer engineering. $3 569006
653 $a Computational ethology
653 $a Computer vision
653 $a Embodied AI
653 $a Pretrained representations
653 $a Robotics
653 $a Transfer learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0463
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Computer Science. $3 1179511
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30427043 $z click for full text (PQDT)