Back to Search Start Over

Artificial intelligence and operations research in maritime logistics

Authors :
Dornemann, Jorin
Rückert, Nicolas
Fischer, Kathrin
Taraz, Anusch
Source :
Hamburg International Conference of Logistics (HICL) 30: 337-381 (2020)
Publication Year :
2020
Publisher :
epubli, 2020.

Abstract

Purpose: The application of artificial intelligence (AI) has the potential to lead to huge progress in combination with Operations Research methods. In our study, we explore current approaches for the usage of AI methods in solving optimization prob-lems. The aim is to give an overview of recent advances and to investigate how they are adapted to maritime logistics. Methodology: A structured literature review is conducted and presented. The iden-tified papers and contributions are categorized and classified, and the content and results of some especially relevant contributions are summarized. Moreover, an eval-uation, identifying existing research gaps and giving an outlook on future research directions, is given. Findings: Besides an inflationary use of AI keywords in the area of optimization, there has been growing interest in using machine learning to automatically learn heuristics for optimization problems. Our research shows that those approaches mostly have not yet been adapted to maritime logistics problems. The gaps identi-fied provide the basis for developing learning models for maritime logistics in future research. Originality: Using methods of machine learning in the area of operations research is a promising and active research field with a wide range of applications. To review these recent advances from a maritime logistics' point of view is a novel approach which could lead to advantages in developing solutions for large-scale optimization problems in maritime logistics in future research and practice.

Details

Language :
English
Database :
OpenAIRE
Journal :
Hamburg International Conference of Logistics (HICL) 30: 337-381 (2020)
Accession number :
edsair.doi.dedup.....ac58629500170f03b707ba2d11ddbc68
Full Text :
https://doi.org/10.15480/882.3140