2023 Fiscal Year Final Research Report
A flexible solver for large scale 3D-bin-packing problem
| Project/Area Number |
21K12030
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
Mashita Tomohiro 大阪大学, サイバーメディアセンター, 准教授 (00467606)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
李 天鎬 岡山理科大学, 総合情報学部, 教授 (70792737)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 3次元パッキング問題 / 遺伝的アルゴリズム |
|---|
| Outline of Final Research Achievements |
In this research project, we developed a method for solving 3D packing problem, which is a meta-heuristic approach with the evaluation of multi-body dynamics. As a result of our research, our method obtained a solution that is robust against shaking during transportation, and we also demonstrated a solution that can be applied to various conditions. In addition, we have improved the learning performance for solving 3D packing problems using deep reinforcement learning.
|
| Free Research Field |
Computer Vision
|
| Academic Significance and Societal Importance of the Research Achievements |
複数の荷物(Cargo) を容器(Container) に詰め込む3 次元パッキング問題は社会の様々な場面で発生している問題である．また，個々の問題はそれぞれに異なる条件を持つため，ヒューリスティックな解法ではそれぞれの条件を組み込んだアルゴリズムの開発が必要であった．対して，本研究ではより現実に近い揺れや積みつけの条件を物理シミュレーションと評価関数の設計という形で実現しており，他様な問題に対応できるため，従来より柔軟で実用的かつ応用範囲の広い解法として社会的・学術的な意義が大きい．
|
