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

Lifelong, Learning-Augmented Robot N...

Doherty, Kevin J.

FindBook

Google Book

Amazon

博客來

Lifelong, Learning-Augmented Robot Navigation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Lifelong, Learning-Augmented Robot Navigation./
作者:	Doherty, Kevin J.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	157 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
標題:	Datasets. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30672360
ISBN:	9798380097376

Lifelong, Learning-Augmented Robot Navigation.
Doherty, Kevin J.

Lifelong, Learning-Augmented Robot Navigation. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 157 p.

Source: Dissertations Abstracts International, Volume: 85-02, Section: B.

Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.

Simultaneous localization and mapping (SLAM) is the process by which a robot constructs a global model of an environment from local observations of it; this is a fundamental perceptual capability supporting planning, navigation, and control. We are interested in improving the expressiveness and operational longevity of SLAM systems. In particular, we are interested in leveraging state-of-the-art machine learning methods for object detection to augment the maps robots can build with object-level semantic information. To do so, a robot must combine continuous geometric information about its trajectory and object locations with discrete semantic information about object classes. This problem is complicated by the fact that object detection techniques are often unreliable in novel environments, introducing outliers and making it difficult to determine the correspondence between detected objects and mapped landmarks. For robust long-term navigation, a robot must contend with these discrete sources of ambiguity. Finally, even when measurements are not corrupted by outliers, long-term SLAM remains a challenging computational problem: typical solution methods rely on local optimization techniques that require a good "initial guess," and whose computational expense grows as measurements accumulate.The first contribution of this thesis addresses the problem of inference for hybrid probabilistic models, i.e. models containing both discrete and continuous states we would like to estimate. These problems frequently arise when modeling e.g., outlier contamination (where binary variables indicate whether a measurement is corrupted), or when performing object-level mapping (where discrete variables may represent measurement-landmark correspondence or object categories). The former application is crucial for designing more robust perception systems. The latter application is especially important for enabling robots to construct semantic maps; that is, maps containing objects whose states are a mixture of continuous geometric information and discrete semantic information. The second contribution of this thesis is a novel spectral initialization method which is efficient to compute, easy to implement, and admits the first formal performance guarantees for a SLAM initialization method. The final contribution of this thesis aims to curtail the growing computational expense of long-term SLAM. In particular, we propose an efficient algorithm for graph sparsification capable of reducing the computational burden of SLAM methods without significantly degrading SLAM solution quality. Taken together, these contributions improve the robustness and efficiency of robot perception approaches in the lifelong setting.

ISBN: 9798380097376Subjects--Topical Terms:

3541416
Datasets.

Lifelong, Learning-Augmented Robot Navigation.
LDR:03769nmm a2200349 4500 001 2401395
005 20241022112605.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380097376
035 $a (MiAaPQ)AAI30672360
035 $a (MiAaPQ)MIT1721_1_150281
035 $a AAI30672360
035 $a 2401395
040 $a MiAaPQ $c MiAaPQ
100 1 $a Doherty, Kevin J. $0 (orcid)0000-0002-8924-2502 $3 3771489
245 1 0 $a Lifelong, Learning-Augmented Robot Navigation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 157 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
500 $a Advisor: Leonard, John J.
502 $a Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.
520 $a Simultaneous localization and mapping (SLAM) is the process by which a robot constructs a global model of an environment from local observations of it; this is a fundamental perceptual capability supporting planning, navigation, and control. We are interested in improving the expressiveness and operational longevity of SLAM systems. In particular, we are interested in leveraging state-of-the-art machine learning methods for object detection to augment the maps robots can build with object-level semantic information. To do so, a robot must combine continuous geometric information about its trajectory and object locations with discrete semantic information about object classes. This problem is complicated by the fact that object detection techniques are often unreliable in novel environments, introducing outliers and making it difficult to determine the correspondence between detected objects and mapped landmarks. For robust long-term navigation, a robot must contend with these discrete sources of ambiguity. Finally, even when measurements are not corrupted by outliers, long-term SLAM remains a challenging computational problem: typical solution methods rely on local optimization techniques that require a good "initial guess," and whose computational expense grows as measurements accumulate.The first contribution of this thesis addresses the problem of inference for hybrid probabilistic models, i.e. models containing both discrete and continuous states we would like to estimate. These problems frequently arise when modeling e.g., outlier contamination (where binary variables indicate whether a measurement is corrupted), or when performing object-level mapping (where discrete variables may represent measurement-landmark correspondence or object categories). The former application is crucial for designing more robust perception systems. The latter application is especially important for enabling robots to construct semantic maps; that is, maps containing objects whose states are a mixture of continuous geometric information and discrete semantic information. The second contribution of this thesis is a novel spectral initialization method which is efficient to compute, easy to implement, and admits the first formal performance guarantees for a SLAM initialization method. The final contribution of this thesis aims to curtail the growing computational expense of long-term SLAM. In particular, we propose an efficient algorithm for graph sparsification capable of reducing the computational burden of SLAM methods without significantly degrading SLAM solution quality. Taken together, these contributions improve the robustness and efficiency of robot perception approaches in the lifelong setting.
590 $a School code: 0753.
650 4 $a Datasets. $3 3541416
650 4 $a Optimization techniques. $3 3681622
650 4 $a Graph representations. $3 3560730
650 4 $a Robots. $3 529507
650 4 $a Design. $3 518875
650 4 $a Algorithms. $3 536374
650 4 $a Vector space. $3 3771490
650 4 $a Localization. $3 3560711
650 4 $a Robotics. $3 519753
650 4 $a Computer science. $3 523869
690 $a 0771
690 $a 0389
690 $a 0984
710 2 $a Massachusetts Institute of Technology. $b Department of Aeronautics and Astronautics. $3 3762524
773 0 $t Dissertations Abstracts International $g 85-02B.
790 $a 0753
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30672360