FamiPacking: A Diffusion Model for Guiding 3D Bin Packing

Chu Jun Peng; Ling Lo; Hongxia Xie; Chien Chih Chiu; Wan Hsin Hsueh; Shih Chieh Huang; Hong Han Shuai; Wen Huang Cheng

doi:10.1049/icp.2023.3199

FamiPacking: A Diffusion Model for Guiding 3D Bin Packing

Chu Jun Peng, Ling Lo, Hongxia Xie, Chien Chih Chiu, Wan Hsin Hsueh, Shih Chieh Huang, Hong Han Shuai, Wen Huang Cheng

Research output: Contribution to journal › Conference article › peer-review

Abstract

3D bin packing (3D-BPP) is one of the most important problems in logistics. To optimize the packaging material usage, we proposed a novel interactive system based on diffusion models for 3D-BPP, namely FamiPacking, which takes the input of data regarding bins and items to be packed and outputs the minimum number of required bins with a visualization instruction. To our knowledge, this is the first diffusion-based system for packing planning. The techniques behind our FamiPacking have been practiced to deal with real-world challenges and improve the packing system of Taiwan FamilyMart (Taiwan's best convenience store chain).

Original language	English
Pages (from-to)	79-80
Number of pages	2
Journal	IET Conference Proceedings
Volume	2023
Issue number	35
DOIs	https://doi.org/10.1049/icp.2023.3199
State	Published - 2023
Event	2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023 - Yunlin, Taiwan Duration: 21 Oct 2023 → 23 Oct 2023

Keywords

3D Bin packing
Diffusion models
Generative AI
Graph modeling

Access to Document

10.1049/icp.2023.3199

Cite this

@article{f45b86d010ee4dceadec7ef682a7b33f,

title = "FamiPacking: A Diffusion Model for Guiding 3D Bin Packing",

abstract = "3D bin packing (3D-BPP) is one of the most important problems in logistics. To optimize the packaging material usage, we proposed a novel interactive system based on diffusion models for 3D-BPP, namely FamiPacking, which takes the input of data regarding bins and items to be packed and outputs the minimum number of required bins with a visualization instruction. To our knowledge, this is the first diffusion-based system for packing planning. The techniques behind our FamiPacking have been practiced to deal with real-world challenges and improve the packing system of Taiwan FamilyMart (Taiwan's best convenience store chain).",

keywords = "3D Bin packing, Diffusion models, Generative AI, Graph modeling",

author = "Peng, {Chu Jun} and Ling Lo and Hongxia Xie and Chiu, {Chien Chih} and Hsueh, {Wan Hsin} and Huang, {Shih Chieh} and Shuai, {Hong Han} and Cheng, {Wen Huang}",

note = "Publisher Copyright: {\textcopyright} The Institution of Engineering & Technology 2023.; 2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023 ; Conference date: 21-10-2023 Through 23-10-2023",

year = "2023",

doi = "10.1049/icp.2023.3199",

language = "English",

volume = "2023",

pages = "79--80",

journal = "IET Conference Proceedings",

issn = "2732-4494",

publisher = "Institution of Engineering and Technology",

number = "35",

}

TY - JOUR

T1 - FamiPacking

T2 - 2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023

AU - Peng, Chu Jun

AU - Lo, Ling

AU - Xie, Hongxia

AU - Chiu, Chien Chih

AU - Hsueh, Wan Hsin

AU - Huang, Shih Chieh

AU - Shuai, Hong Han

AU - Cheng, Wen Huang

N1 - Publisher Copyright: © The Institution of Engineering & Technology 2023.

PY - 2023

Y1 - 2023

N2 - 3D bin packing (3D-BPP) is one of the most important problems in logistics. To optimize the packaging material usage, we proposed a novel interactive system based on diffusion models for 3D-BPP, namely FamiPacking, which takes the input of data regarding bins and items to be packed and outputs the minimum number of required bins with a visualization instruction. To our knowledge, this is the first diffusion-based system for packing planning. The techniques behind our FamiPacking have been practiced to deal with real-world challenges and improve the packing system of Taiwan FamilyMart (Taiwan's best convenience store chain).

AB - 3D bin packing (3D-BPP) is one of the most important problems in logistics. To optimize the packaging material usage, we proposed a novel interactive system based on diffusion models for 3D-BPP, namely FamiPacking, which takes the input of data regarding bins and items to be packed and outputs the minimum number of required bins with a visualization instruction. To our knowledge, this is the first diffusion-based system for packing planning. The techniques behind our FamiPacking have been practiced to deal with real-world challenges and improve the packing system of Taiwan FamilyMart (Taiwan's best convenience store chain).

KW - 3D Bin packing

KW - Diffusion models

KW - Generative AI

KW - Graph modeling

UR - http://www.scopus.com/inward/record.url?scp=85188444587&partnerID=8YFLogxK

U2 - 10.1049/icp.2023.3199

DO - 10.1049/icp.2023.3199

M3 - Conference article

AN - SCOPUS:85188444587

SN - 2732-4494

VL - 2023

SP - 79

EP - 80

JO - IET Conference Proceedings

JF - IET Conference Proceedings

IS - 35

Y2 - 21 October 2023 through 23 October 2023

ER -

FamiPacking: A Diffusion Model for Guiding 3D Bin Packing

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this