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

Hierarchical Decision-Making in Coordinated Multi-Robot Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Hierarchical Decision-Making in Coordinated Multi-Robot Networks./
作者:	Choudhury, Shushman.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	196 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Software quality. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28671153
ISBN:	9798544200291

Hierarchical Decision-Making in Coordinated Multi-Robot Networks.
Choudhury, Shushman.

Hierarchical Decision-Making in Coordinated Multi-Robot Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 196 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

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

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

Autonomous robots are deployed to solve a variety of tasks in a wide range of challenging and uncertain environments. Many of the tasks, such as urban package delivery and planetary terrain exploration involve connected networks of robots operating with and around each other. This thesis presents a comprehensive decision-making framework for controlling such large multi-robot networks.Coordinating robots in the network enables them to team up dynamically, such as ground rovers carrying copters to launch points or delivery drones riding on trucks for segments of their route. Such coordination can make these networks cheaper and more energy-efficient. But it greatly exacerbates the daunting computational challenges for operating multi-robot networks under the uncertainty of the world. For instance, if any drone can leverage one or more trucks for some route intervals, we need to decide whether to do so and for how long. If the ability of a drone to make a delivery depends on it using the trucks, we also need to care about truck delays or speedups and their downstream effects. Furthermore, we will need to address these challenges for all of our drones and trucks collectively.This thesis develops decision-making algorithms that decouple the many complex intersecting challenges of our overall question and address them at different levels in a hierarchy: allocating tasks to agents at the highest level, followed by planning routes for agents to coordinate with each other, followed by controlling the agents to execute their planned routes while adapting quickly to new information and tasks. Our design of these algorithms is also guided by the challenges and opportunities that coordination brings with it, in particular how those challenges affect the interaction between the layers of the hierarchy.To address the range of problems covered in this thesis, we draw upon theoretical results from combinatorial optimization, heuristic search, and sequential decisionmaking under uncertainty. We extend theory to application through state-of-theart practical techniques for multi-agent methods and efficient yet easily reproducible implementations in the high-level Julia programming language. On a wide variety of simulations with real-world data, our algorithms demonstrate good tradeoffs between computing high-quality decisions on our desired metrics and efficiently solving for large numbers of agents and tasks.

ISBN: 9798544200291Subjects--Topical Terms:

3562903
Software quality.

Hierarchical Decision-Making in Coordinated Multi-Robot Networks.
LDR:03510nmm a2200325 4500 001 2344854
005 20220531062158.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798544200291
035 $a (MiAaPQ)AAI28671153
035 $a (MiAaPQ)STANFORDxt716fk9099
035 $a AAI28671153
040 $a MiAaPQ $c MiAaPQ
100 1 $a Choudhury, Shushman. $3 3683678
245 1 0 $a Hierarchical Decision-Making in Coordinated Multi-Robot Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 196 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Kochenderfer, Mykel;Bohg, Jeannette;Pavone, Marco;Sadigh, Dorsa.
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 are deployed to solve a variety of tasks in a wide range of challenging and uncertain environments. Many of the tasks, such as urban package delivery and planetary terrain exploration involve connected networks of robots operating with and around each other. This thesis presents a comprehensive decision-making framework for controlling such large multi-robot networks.Coordinating robots in the network enables them to team up dynamically, such as ground rovers carrying copters to launch points or delivery drones riding on trucks for segments of their route. Such coordination can make these networks cheaper and more energy-efficient. But it greatly exacerbates the daunting computational challenges for operating multi-robot networks under the uncertainty of the world. For instance, if any drone can leverage one or more trucks for some route intervals, we need to decide whether to do so and for how long. If the ability of a drone to make a delivery depends on it using the trucks, we also need to care about truck delays or speedups and their downstream effects. Furthermore, we will need to address these challenges for all of our drones and trucks collectively.This thesis develops decision-making algorithms that decouple the many complex intersecting challenges of our overall question and address them at different levels in a hierarchy: allocating tasks to agents at the highest level, followed by planning routes for agents to coordinate with each other, followed by controlling the agents to execute their planned routes while adapting quickly to new information and tasks. Our design of these algorithms is also guided by the challenges and opportunities that coordination brings with it, in particular how those challenges affect the interaction between the layers of the hierarchy.To address the range of problems covered in this thesis, we draw upon theoretical results from combinatorial optimization, heuristic search, and sequential decisionmaking under uncertainty. We extend theory to application through state-of-theart practical techniques for multi-agent methods and efficient yet easily reproducible implementations in the high-level Julia programming language. On a wide variety of simulations with real-world data, our algorithms demonstrate good tradeoffs between computing high-quality decisions on our desired metrics and efficiently solving for large numbers of agents and tasks.
590 $a School code: 0212.
650 4 $a Software quality. $3 3562903
650 4 $a Integer programming. $3 648270
650 4 $a Control algorithms. $3 3560702
650 4 $a Teams. $3 3546566
650 4 $a Planning. $3 552734
650 4 $a Optimization. $3 891104
650 4 $a Decision making. $3 517204
650 4 $a Robots. $3 529507
650 4 $a Linear programming. $3 560448
650 4 $a Drones. $3 3549538
650 4 $a Energy. $3 876794
650 4 $a Research & development--R&D. $3 3554335
650 4 $a Traffic congestion. $3 706812
650 4 $a Robotics. $3 519753
650 4 $a Vehicles. $3 2145288
650 4 $a Operations research. $3 547123
650 4 $a Experiments. $3 525909
650 4 $a Variables. $3 3548259
690 $a 0771
690 $a 0791
690 $a 0796
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-03B.
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=28671153