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

回上頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Active Localization for Robotic Systems: Algorithms and Cost Metrics.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Active Localization for Robotic Systems: Algorithms and Cost Metrics./
作者:	Strader, Jared.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	186 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: A.
Contained By:	Dissertations Abstracts International83-05A.
標題:	Autonomous underwater vehicles. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28811966
ISBN:	9798494452436

Active Localization for Robotic Systems: Algorithms and Cost Metrics.
Strader, Jared.

Active Localization for Robotic Systems: Algorithms and Cost Metrics. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 186 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: A.

Thesis (Ph.D.)--West Virginia University, 2021.

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

In the real world, a robotic system must operate in the presence of motion and sensing uncertainty. This is caused by the fact that the motion of a robotic system is stochastic due to disturbances from the environment, and the states are only partially observable due noise in the sensor measurements. As a result, the true state of a robotic system is unknown, and estimation techniques must be used to infer the states from the belief, which is the probability distribution over all possible states. Accordingly, a robotic system must be capable of reasoning about the quality of the belief at future time steps to manage the growth of uncertainty by choosing the correct actions. This is problem is referred to as active localization and is the problem addressed in this dissertation.The goal of active localization is to plan a sensor trajectory that minimizes the growth uncertainty potentially along with additional objectivesThis problem can be formulated as a Partially Observable Markov Decision Process (POMDP), which is a mathematical framework for modelling sequential decision making problems inthe presence of uncertainty. However, obtaining an exact solutionto a POMDP is an intractable problem in general, and only a few problems formulated as POMDPs can be solved exactly. While significant progress has been made in recent years towards approximately solving POMDPs, existing methods suffer from suboptimality for problems where the objective is to reach a particular state. This dissertation considers approximate POMDP solutions and seeks to quantify the utility for active localization under various assumptions This dissertation can be separated in three main parts. First, uncertainty metrics (such as the A-, E-, and D-optimality criteria) are analyzed, which are necessary for quantifying uncertainty associated with the belief. A metric is proposed extending the criteria that allows for efficiently quantifying uncertainty at future time steps. Second, the metrics are analyzed assuming only the most likely measurements are acquired during runtime, and a method is proposed called the D-optimality Roadmap (DORM) for motion planning assuming the belief is Gaussian. Third, heuristics are introduced for approximated the uncertainty at future time steps under the best-case and worst-case scenarios. The heuristics provide upper and lower bounds on the optimality criteria, which can be used for sampling paths pessimistically or optimistically, which can be used to quickly plan trajectories for active localization.

ISBN: 9798494452436Subjects--Topical Terms:

3444520
Autonomous underwater vehicles.

Active Localization for Robotic Systems: Algorithms and Cost Metrics.
LDR:03630nmm a2200361 4500 001 2344692
005 20220531064627.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798494452436
035 $a (MiAaPQ)AAI28811966
035 $a (MiAaPQ)WVirginia9307
035 $a AAI28811966
040 $a MiAaPQ $c MiAaPQ
100 1 $a Strader, Jared. $3 3683485
245 1 0 $a Active Localization for Robotic Systems: Algorithms and Cost Metrics.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 186 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: A.
500 $a Advisor: Gu, Yu.
502 $a Thesis (Ph.D.)--West Virginia University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a In the real world, a robotic system must operate in the presence of motion and sensing uncertainty. This is caused by the fact that the motion of a robotic system is stochastic due to disturbances from the environment, and the states are only partially observable due noise in the sensor measurements. As a result, the true state of a robotic system is unknown, and estimation techniques must be used to infer the states from the belief, which is the probability distribution over all possible states. Accordingly, a robotic system must be capable of reasoning about the quality of the belief at future time steps to manage the growth of uncertainty by choosing the correct actions. This is problem is referred to as active localization and is the problem addressed in this dissertation.The goal of active localization is to plan a sensor trajectory that minimizes the growth uncertainty potentially along with additional objectivesThis problem can be formulated as a Partially Observable Markov Decision Process (POMDP), which is a mathematical framework for modelling sequential decision making problems inthe presence of uncertainty. However, obtaining an exact solutionto a POMDP is an intractable problem in general, and only a few problems formulated as POMDPs can be solved exactly. While significant progress has been made in recent years towards approximately solving POMDPs, existing methods suffer from suboptimality for problems where the objective is to reach a particular state. This dissertation considers approximate POMDP solutions and seeks to quantify the utility for active localization under various assumptions This dissertation can be separated in three main parts. First, uncertainty metrics (such as the A-, E-, and D-optimality criteria) are analyzed, which are necessary for quantifying uncertainty associated with the belief. A metric is proposed extending the criteria that allows for efficiently quantifying uncertainty at future time steps. Second, the metrics are analyzed assuming only the most likely measurements are acquired during runtime, and a method is proposed called the D-optimality Roadmap (DORM) for motion planning assuming the belief is Gaussian. Third, heuristics are introduced for approximated the uncertainty at future time steps under the best-case and worst-case scenarios. The heuristics provide upper and lower bounds on the optimality criteria, which can be used for sampling paths pessimistically or optimistically, which can be used to quickly plan trajectories for active localization.
590 $a School code: 0256.
650 4 $a Autonomous underwater vehicles. $3 3444520
650 4 $a Robots. $3 529507
650 4 $a Global positioning systems--GPS. $3 3559357
650 4 $a Mathematical functions. $3 3564295
650 4 $a Unmanned aerial vehicles. $3 3560267
650 4 $a Algorithms. $3 536374
650 4 $a Localization. $3 3560711
650 4 $a Sensors. $3 3549539
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Computer science. $3 523869
650 4 $a Engineering. $3 586835
650 4 $a Mathematics. $3 515831
650 4 $a Robotics. $3 519753
650 4 $a Transportation. $3 555912
690 $a 0538
690 $a 0984
690 $a 0537
690 $a 0405
690 $a 0771
690 $a 0709
710 2 $a West Virginia University. $3 1017532
773 0 $t Dissertations Abstracts International $g 83-05A.
790 $a 0256
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28811966