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

Learning-Based Perception for Roboti...

Lee, Connor Tinghan,

FindBook

Google Book

Amazon

博客來

Learning-Based Perception for Robotics in Suboptimal Data Landscapes /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Learning-Based Perception for Robotics in Suboptimal Data Landscapes // Connor Tinghan Lee.
作者:	Lee, Connor Tinghan,
面頁冊數:	1 electronic resource (183 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-04, Section: A.
Contained By:	Dissertations Abstracts International86-04A.
標題:	Creeks & streams. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31524086
ISBN:	9798342114677

Learning-Based Perception for Robotics in Suboptimal Data Landscapes /
Lee, Connor Tinghan,

Learning-Based Perception for Robotics in Suboptimal Data Landscapes /Connor Tinghan Lee. - 1 electronic resource (183 pages)

Source: Dissertations Abstracts International, Volume: 86-04, Section: A.

Autonomous robots are increasingly present in the world today, being used across a variety of settings and applications. In order to interact with their surroundings, robots typically use cameras to see the world, employing computer vision algorithms to comprehend rich, visual information. While contemporary, learning-based computer vision models provide robots with an accurate and robust understanding of their surroundings, most off-the-shelf methods rely on supervised deep learning techniques, requiring abundant labeled data in order to train and prevent overfitting. However, in many robotic applications and settings, the data landscape is characterized by data scarcity and/or the lack of apparent supervisory signals. Since custom perception solutions are often required for robotic applications, direct adoption of common computer vision methods proves challenging.In this thesis, we develop robotic perception approaches across three different applications that overcome the challenges of such data landscapes. First, we develop learning-based visual terrain-relative navigation (VTRN) approaches for high-altitude aerial vehicles. This is a problem for which relevant data is available, but made difficult by the lack of obvious supervisory signals related to the high-level navigation objective. In the first chapters of the thesis, we show the power of self-supervised learning approaches to increase VTRN robustness to seasonal and temporal variations that would otherwise debilitate such systems.Next, we address the challenge of developing thermal semantic perception algorithms for aerial field robotics. Due to the specialized nature of field environments and the sensing modality, development of thermal vision algorithms under these conditions is often characterized by the lack of relevant data. We show how we develop various thermal semantic segmentation in response to the evolving data constraints inherent in field robotic projects. In the final part of the thesis, we develop data-efficient, multispectral deep learning algorithms for autonomous driving applications where the lack of data arises from the need for custom, multispectral datasets that are synchronized and coregistered.

English

ISBN: 9798342114677Subjects--Topical Terms:

3685269
Creeks & streams.

Learning-Based Perception for Robotics in Suboptimal Data Landscapes /
LDR:03563nmm a22003973i 4500 001 2428602
005 20250414021909.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798342114677
035 $a (MiAaPQD)AAI31524086
035 $a (MiAaPQD)Caltech16485
035 $a AAI31524086
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Lee, Connor Tinghan, $e author. $3 3815927
245 1 0 $a Learning-Based Perception for Robotics in Suboptimal Data Landscapes / $c Connor Tinghan Lee.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (183 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: 86-04, Section: A.
500 $a Advisors: Chung, Soon-Jo Committee members: Watkins, Michael; Gkioxari, Georgia; Hadaegh, Fred.
502 $b Ph.D. $c California Institute of Technology $d 2024.
520 $a Autonomous robots are increasingly present in the world today, being used across a variety of settings and applications. In order to interact with their surroundings, robots typically use cameras to see the world, employing computer vision algorithms to comprehend rich, visual information. While contemporary, learning-based computer vision models provide robots with an accurate and robust understanding of their surroundings, most off-the-shelf methods rely on supervised deep learning techniques, requiring abundant labeled data in order to train and prevent overfitting. However, in many robotic applications and settings, the data landscape is characterized by data scarcity and/or the lack of apparent supervisory signals. Since custom perception solutions are often required for robotic applications, direct adoption of common computer vision methods proves challenging.In this thesis, we develop robotic perception approaches across three different applications that overcome the challenges of such data landscapes. First, we develop learning-based visual terrain-relative navigation (VTRN) approaches for high-altitude aerial vehicles. This is a problem for which relevant data is available, but made difficult by the lack of obvious supervisory signals related to the high-level navigation objective. In the first chapters of the thesis, we show the power of self-supervised learning approaches to increase VTRN robustness to seasonal and temporal variations that would otherwise debilitate such systems.Next, we address the challenge of developing thermal semantic perception algorithms for aerial field robotics. Due to the specialized nature of field environments and the sensing modality, development of thermal vision algorithms under these conditions is often characterized by the lack of relevant data. We show how we develop various thermal semantic segmentation in response to the evolving data constraints inherent in field robotic projects. In the final part of the thesis, we develop data-efficient, multispectral deep learning algorithms for autonomous driving applications where the lack of data arises from the need for custom, multispectral datasets that are synchronized and coregistered.
546 $a English
590 $a School code: 0037
650 4 $a Creeks & streams. $3 3685269
650 4 $a Robots. $3 529507
650 4 $a Adaptation. $3 3562958
650 4 $a Online instruction. $3 3562296
650 4 $a Registration. $3 3682192
650 4 $a Visualization. $3 586179
650 4 $a Distance learning. $3 3557921
650 4 $a Semantics. $3 520060
650 4 $a Robotics. $3 519753
650 4 $a Aquatic sciences. $3 3174300
650 4 $a Educational technology. $3 517670
650 4 $a Logic. $3 529544
690 $a 0771
690 $a 0792
690 $a 0710
690 $a 0395
710 2 $a California Institute of Technology. $b Engineering and Applied Science. $e degree granting institution. $3 3765818
720 1 $a Chung, Soon-Jo $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-04A.
790 $a 0037
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31524086