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

Compositional Reasoning in Robot Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Compositional Reasoning in Robot Learning./
作者:	Xu, Danfei.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	120 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Robots. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28827908
ISBN:	9798494461704

Compositional Reasoning in Robot Learning.
Xu, Danfei.

Compositional Reasoning in Robot Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 120 p.

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

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

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

To carry out diverse tasks in everyday human environments, future robots must generalize beyond the knowledge they are equipped with. However, despite recent advances in "end-to-end" deep learning, today's robot learning methods are still limited to specializing in one task at a time. At the same time, humans perform everyday tasks with ease. But instead of learning each task in silos, we distill reusable abstractions from our daily experiences and solve new tasks by composing known building blocks. Such compositional reasoning capability is crucial for developing future robots that are both competent and versatile.This two-part thesis presents a spectrum of techniques for building compositional generalization capabilities into robot learning systems. Part I starts by drawing prominent ideas from classical structured approaches in AI such as program induction and graphical models and design algorithms with strong representational priors. Neural Task Programming (NTP) represents task-subtask hierarchies using modular neural programs. NTP is designed to simultaneously exploit the representational capacity of neural networks for handling unstructured input and the compositional nature of programs for few-shot generalization. Similarly, Neural Task Graphs (NTGs) represent manipulation skills as nodes in a graph and leverage structures in skill preconditions for generalization. Regression Planning Network (RPN) further dissects the goal specification by grounding symbolic goals with object-centric representation and achieve zero-shot generalization to new task goals.To bring compositional reasoning closer to real-world settings, Part II of this thesis introduces our recent efforts to relax the strong representational prior assumptions: learning from unstructured video demonstrations and learning through trial-and-error. We first describe a framework for simultaneously learning complex visuomotor skills and discovering implicit compositional structures from human demonstrations. Experiment shows the approach allows a physical robot to perform long-horizon manipulation in a kitchen setup. Then we further relax the assumption of having demonstration data and enable a robot to learn compact planning representations by characterizing the pre- and post-condition of motion primitives through active interaction.

ISBN: 9798494461704Subjects--Topical Terms:

529507
Robots.

Compositional Reasoning in Robot Learning.
LDR:03430nmm a2200349 4500 001 2344699
005 20220531064629.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798494461704
035 $a (MiAaPQ)AAI28827908
035 $a (MiAaPQ)STANFORDys432pr6718
035 $a AAI28827908
040 $a MiAaPQ $c MiAaPQ
100 1 $a Xu, Danfei. $3 3683498
245 1 0 $a Compositional Reasoning in Robot Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 120 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Savarese, Silvio;Li, Fei-Fei;Bohg, Jeannette;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 To carry out diverse tasks in everyday human environments, future robots must generalize beyond the knowledge they are equipped with. However, despite recent advances in "end-to-end" deep learning, today's robot learning methods are still limited to specializing in one task at a time. At the same time, humans perform everyday tasks with ease. But instead of learning each task in silos, we distill reusable abstractions from our daily experiences and solve new tasks by composing known building blocks. Such compositional reasoning capability is crucial for developing future robots that are both competent and versatile.This two-part thesis presents a spectrum of techniques for building compositional generalization capabilities into robot learning systems. Part I starts by drawing prominent ideas from classical structured approaches in AI such as program induction and graphical models and design algorithms with strong representational priors. Neural Task Programming (NTP) represents task-subtask hierarchies using modular neural programs. NTP is designed to simultaneously exploit the representational capacity of neural networks for handling unstructured input and the compositional nature of programs for few-shot generalization. Similarly, Neural Task Graphs (NTGs) represent manipulation skills as nodes in a graph and leverage structures in skill preconditions for generalization. Regression Planning Network (RPN) further dissects the goal specification by grounding symbolic goals with object-centric representation and achieve zero-shot generalization to new task goals.To bring compositional reasoning closer to real-world settings, Part II of this thesis introduces our recent efforts to relax the strong representational prior assumptions: learning from unstructured video demonstrations and learning through trial-and-error. We first describe a framework for simultaneously learning complex visuomotor skills and discovering implicit compositional structures from human demonstrations. Experiment shows the approach allows a physical robot to perform long-horizon manipulation in a kitchen setup. Then we further relax the assumption of having demonstration data and enable a robot to learn compact planning representations by characterizing the pre- and post-condition of motion primitives through active interaction.
590 $a School code: 0212.
650 4 $a Robots. $3 529507
650 4 $a Deep learning. $3 3554982
650 4 $a Algorithms. $3 536374
650 4 $a Ablation. $3 3562462
650 4 $a Intelligence. $3 590016
650 4 $a Planning. $3 552734
650 4 $a Neural networks. $3 677449
650 4 $a Cognition & reasoning. $3 3556293
650 4 $a Artificial intelligence. $3 516317
650 4 $a Cognitive psychology. $3 523881
650 4 $a Computer science. $3 523869
650 4 $a Psychology. $3 519075
650 4 $a Robotics. $3 519753
690 $a 0800
690 $a 0633
690 $a 0984
690 $a 0621
690 $a 0771
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-05B.
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=28827908