東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

See, Act, and Conceptualize: A Learning System for Robots to Interact with the World.

Record Type:	Electronic resources : Monograph/item
Title/Author:	See, Act, and Conceptualize: A Learning System for Robots to Interact with the World./
Author:	Shao, Lin.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	115 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
Subject:	Fixtures. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28688320
ISBN:	9798544203742

See, Act, and Conceptualize: A Learning System for Robots to Interact with the World.
Shao, Lin.

See, Act, and Conceptualize: A Learning System for Robots to Interact with the World. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 115 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.

Building intelligent systems for robots to interact with the world is a challenging problem due to many factors, such as the high dimensionality of the state and action space, the enormous variability of tasks, and the uncertainty of surrounding environments. This dissertation contains our work to guide robots to learn to perceive objects and motion, master various manipulation skills, and develop concepts to better interact with the world. Robots need to develop their visual systems to perceive objects and motion. When robots start to move and interact with surrounding environments, they thereby autonomously induce motion in the scene. Such motion creates a rich, visual sensory signal facilitating better scene understanding. We introduce our work that jointly estimates the segmentation of a scene into a finite number of rigidly moving objects, the motion trajectories of these objects, and the object scene flow. After robots perceive objects, they can move their hands to manipulate these objects. We present our approaches to train robots to master various primitive and complex manipulation skills. Choosing the right action representation is important to master primitive skills. We present a data-driven grasp synthesis method that considers both the object geometry and gripper attributes. Our method leverages contact points as an abstraction that can be re-used by a diverse set of robot hands. Besides contact points between objects and robotic hands, we propose a contact point matching representation between two objects and utilize it to train robots to learn how to hang arbitrary objects onto diverse supporting items such as racks or hooks. For complex skills such as tool manipulation and robotic assembly, we describe a learning framework that allows a robot to autonomously modify the environment and discover how to ease manipulation skill learning. As robots master more and more skills, it becomes important for robots to learn to abstract and represent these skills. We present our learning framework that endows robots with the ability to acquire various concepts to represent manipulation skills. These manipulation concepts act as mental representations of verbs in natural language instructions. We propose a learning from demonstration approach to learn manipulation actions from large-scale video data sets that are annotated with natural language instructions. Thus, we could use natural language instructions to guide robots to better interact with the world. We conclude by summarizing our efforts and discuss future directions.

ISBN: 9798544203742Subjects--Topical Terms:

3689259
Fixtures.

See, Act, and Conceptualize: A Learning System for Robots to Interact with the World.
LDR:03620nmm a2200313 4500 001 2349837
005 20221010063635.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798544203742
035 $a (MiAaPQ)AAI28688320
035 $a (MiAaPQ)STANFORDbd998td4251
035 $a AAI28688320
040 $a MiAaPQ $c MiAaPQ
100 1 $a Shao, Lin. $3 3689258
245 1 0 $a See, Act, and Conceptualize: A Learning System for Robots to Interact with the World.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 115 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Bohg, Jeannette; Guibas, Leonidas.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Building intelligent systems for robots to interact with the world is a challenging problem due to many factors, such as the high dimensionality of the state and action space, the enormous variability of tasks, and the uncertainty of surrounding environments. This dissertation contains our work to guide robots to learn to perceive objects and motion, master various manipulation skills, and develop concepts to better interact with the world. Robots need to develop their visual systems to perceive objects and motion. When robots start to move and interact with surrounding environments, they thereby autonomously induce motion in the scene. Such motion creates a rich, visual sensory signal facilitating better scene understanding. We introduce our work that jointly estimates the segmentation of a scene into a finite number of rigidly moving objects, the motion trajectories of these objects, and the object scene flow. After robots perceive objects, they can move their hands to manipulate these objects. We present our approaches to train robots to master various primitive and complex manipulation skills. Choosing the right action representation is important to master primitive skills. We present a data-driven grasp synthesis method that considers both the object geometry and gripper attributes. Our method leverages contact points as an abstraction that can be re-used by a diverse set of robot hands. Besides contact points between objects and robotic hands, we propose a contact point matching representation between two objects and utilize it to train robots to learn how to hang arbitrary objects onto diverse supporting items such as racks or hooks. For complex skills such as tool manipulation and robotic assembly, we describe a learning framework that allows a robot to autonomously modify the environment and discover how to ease manipulation skill learning. As robots master more and more skills, it becomes important for robots to learn to abstract and represent these skills. We present our learning framework that endows robots with the ability to acquire various concepts to represent manipulation skills. These manipulation concepts act as mental representations of verbs in natural language instructions. We propose a learning from demonstration approach to learn manipulation actions from large-scale video data sets that are annotated with natural language instructions. Thus, we could use natural language instructions to guide robots to better interact with the world. We conclude by summarizing our efforts and discuss future directions.
590 $a School code: 0212.
650 4 $a Fixtures. $3 3689259
650 4 $a Performance evaluation. $3 3562292
650 4 $a Neural networks. $3 677449
650 4 $a Robotics. $3 519753
650 4 $a Skills. $3 3221615
650 4 $a Artificial intelligence. $3 516317
690 $a 0771
690 $a 0800
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=28688320