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

Driving Reasoning Systems for Produc...

Bharadwaj, Akshay Ganesh.

Linked to FindBook

Google Book

Amazon

博客來

Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs./
Author:	Bharadwaj, Akshay Ganesh.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	121 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
Contained By:	Dissertations Abstracts International85-06A.
Subject:	Explicit knowledge. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30727245
ISBN:	9798381021028

Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.
Bharadwaj, Akshay Ganesh.

Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 121 p.

Source: Dissertations Abstracts International, Volume: 85-06, Section: A.

Thesis (Ph.D.)--North Carolina State University, 2023.

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

Product Design based Knowledge graphs (KG) aid the representation of product assemblies through heterogeneous relationships that link entities obtained from multiple structured and unstructured sources. This dissertation describes an approach to constructing a multi-relational and multi-hierarchical knowledge graph that extracts information contained within the 3D product model data to construct Assembly-Subassembly-Part and Shape Similarity relationships. This approach builds on a combination of utilizing 3D model meta-data and structuring the graph using the Assembly-Part hierarchy alongside 3D Shape-based Clustering. To demonstrate our approach, from a dataset consisting of 110,770 CAD models, 92,715 models were organized into 7,651 groups of varying sizes containing highly similar shapes, demonstrating the varied nature of design repositories, but inevitably also containing a significant number of repetitive and unique designs. Using the Product Design Knowledge Graph, we demonstrate the effectiveness of 3D shape retrieval using Approximate Nearest Neighbor search. We also illustrate the use of the KG for Design Reuse of co-occurring components, Rule-Based Inference for Assembly Similarity and Collaborative Filtering for Multi-Modal Search of manufacturing process conditions.The application of robots in manufacturing environments has reached a high level of maturity, with advanced machine learning being increasingly used in conjunction with welldeveloped control systems. However, due to the specialized nature of applications such as robotic joining and assembly, repeatable but rigid programming-based control dominates industrial applications. Current applications in this domain driven by the latest trends in the Industry 4.0/ Smart Manufacturing paradigm requires robots to adapt to a variety of work operations and environments, while maintaining accurate and efficient performance. However, there is a gap between the semantic understanding of the machines and the parts being manufactured. This work proposes a method to leverage autonomous object-level perception for flexible robotic manipulation and assembly operations by linking semantic information from CAD data to real-world scenes. By creating pixel-to-surface correspondences between the environment and the source CAD file, we demonstrate a method to create Scene Graphs based on 6D Pose estimates of the object and the hierarchical part data in combination with product manufacturing information (PMI). The application of this method is demonstrated through a sequential robotic manipulation and assembly planning task.

ISBN: 9798381021028Subjects--Topical Terms:

3682762
Explicit knowledge.

Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.
LDR:03780nmm a2200349 4500 001 2393707
005 20240414211523.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798381021028
035 $a (MiAaPQ)AAI30727245
035 $a (MiAaPQ)NCState_Univ18402041238
035 $a AAI30727245
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bharadwaj, Akshay Ganesh. $3 3698570
245 1 0 $a Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 121 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
500 $a Advisor: Ogan, Kemafor Anyanwu.
502 $a Thesis (Ph.D.)--North Carolina State University, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Product Design based Knowledge graphs (KG) aid the representation of product assemblies through heterogeneous relationships that link entities obtained from multiple structured and unstructured sources. This dissertation describes an approach to constructing a multi-relational and multi-hierarchical knowledge graph that extracts information contained within the 3D product model data to construct Assembly-Subassembly-Part and Shape Similarity relationships. This approach builds on a combination of utilizing 3D model meta-data and structuring the graph using the Assembly-Part hierarchy alongside 3D Shape-based Clustering. To demonstrate our approach, from a dataset consisting of 110,770 CAD models, 92,715 models were organized into 7,651 groups of varying sizes containing highly similar shapes, demonstrating the varied nature of design repositories, but inevitably also containing a significant number of repetitive and unique designs. Using the Product Design Knowledge Graph, we demonstrate the effectiveness of 3D shape retrieval using Approximate Nearest Neighbor search. We also illustrate the use of the KG for Design Reuse of co-occurring components, Rule-Based Inference for Assembly Similarity and Collaborative Filtering for Multi-Modal Search of manufacturing process conditions.The application of robots in manufacturing environments has reached a high level of maturity, with advanced machine learning being increasingly used in conjunction with welldeveloped control systems. However, due to the specialized nature of applications such as robotic joining and assembly, repeatable but rigid programming-based control dominates industrial applications. Current applications in this domain driven by the latest trends in the Industry 4.0/ Smart Manufacturing paradigm requires robots to adapt to a variety of work operations and environments, while maintaining accurate and efficient performance. However, there is a gap between the semantic understanding of the machines and the parts being manufactured. This work proposes a method to leverage autonomous object-level perception for flexible robotic manipulation and assembly operations by linking semantic information from CAD data to real-world scenes. By creating pixel-to-surface correspondences between the environment and the source CAD file, we demonstrate a method to create Scene Graphs based on 6D Pose estimates of the object and the hierarchical part data in combination with product manufacturing information (PMI). The application of this method is demonstrated through a sequential robotic manipulation and assembly planning task.
590 $a School code: 0155.
650 4 $a Explicit knowledge. $3 3682762
650 4 $a Ontology. $3 530874
650 4 $a Decision making. $3 517204
650 4 $a Neural networks. $3 677449
650 4 $a Industrial engineering. $3 526216
690 $a 0800
690 $a 0546
690 $a 0338
710 2 $a North Carolina State University. $3 1018772
773 0 $t Dissertations Abstracts International $g 85-06A.
790 $a 0155
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30727245