國立虎尾科技大學 |

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

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs./
作者:	Bharadwaj, Akshay Ganesh.
面頁冊數:	1 online resource (121 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
Contained By:	Dissertations Abstracts International85-06A.
標題:	Industrial engineering. -
電子資源:	click for full text (PQDT)
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. - 1 online resource (121 pages)

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

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

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381021028Subjects--Topical Terms:

679492
Industrial engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.
LDR:03933ntm a22003497 4500 001 1141803
005 20240414211523.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381021028
035 $a (MiAaPQ)AAI30727245
035 $a (MiAaPQ)NCState_Univ18402041238
035 $a AAI30727245
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Bharadwaj, Akshay Ganesh. $3 1465792
245 1 0 $a Driving Reasoning Systems for Product Design and Flexible Robotic Manipulation Using 3D Design-Based Knowledge Graphs.
264 0 $c 2023
300 $a 1 online resource (121 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
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.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Industrial engineering. $3 679492
650 4 $a Neural networks. $3 1011215
650 4 $a Decision making. $3 528319
650 4 $a Ontology. $3 559386
650 4 $a Explicit knowledge. $3 1465793
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0546
690 $a 0338
710 2 $a North Carolina State University. $3 845424
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-06A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30727245 $z click for full text (PQDT)