Neural Combinatorial Optimization on Heterogeneous Graphs: An Application to the Picker Routing Problem in Mixed-Shelves Warehouses

Research output: Journal contributionsConference article in journalResearchpeer-review

Authors

In recent years, machine learning (ML) models capable of solving combinatorial optimization (CO) problems have received a surge of attention. While early approaches failed to outperform traditional CO solvers, the gap between handcrafted and learned heuristics has been steadily closing. However, most work in this area has focused on simple CO problems to benchmark new models and algorithms, leaving a gap in the development of methods specifically designed to handle more involved problems. Therefore, this work considers the problem of picker routing in the context of mixed-shelves warehouses, which involves not only a heterogeneous graph representation, but also a combinatorial action space resulting from the integrated selection and routing decisions to be made. We propose both a novel encoder to effectively learn representations of the heterogeneous graph and a hierarchical decoding scheme that exploits the combinatorial structure of the action space. The efficacy of the developed methods is demonstrated through a comprehensive comparison with established architectures as well as exact and heuristic solvers.

Original languageEnglish
JournalProceedings International Conference on Automated Planning and Scheduling, ICAPS
Volume34
Pages (from-to)351-359
Number of pages9
ISSN2334-0835
DOIs
Publication statusPublished - 30.05.2024
Event34th International Conference on Automated Planning and Scheduling - Banff, Canada
Duration: 01.06.202406.06.2024
Conference number: 34
https://icaps24.icaps-conference.org/

Bibliographical note

Publisher Copyright:
Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Recently viewed

Publications

  1. Analyzing different types of moderated method effects in confirmatory factor models for structurally different methods
  2. Finding Similar Movements in Positional Data Streams
  3. Using mixture distribution models to test the construct validity of the Physical Self-Description Questionnaire
  4. Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations
  5. Lyapunov Convergence Analysis for Asymptotic Tracking Using Forward and Backward Euler Approximation of Discrete Differential Equations
  6. Credit constraints and exports
  7. Comparison of Trajectory Estimation Methods Based on LIDAR and Monocular Camera in a Simulated Environment
  8. Neural relational inference for disaster multimedia retrieval
  9. Development and comparison of processing maps of Mg-3Sn-1Ca alloy from data obtained in tension versus compression
  10. Graph-based Approaches for Analyzing Team Interaction on the Example of Soccer
  11. Influence of Long-Lasting Static Stretching Intervention on Functional and Morphological Parameters in the Plantar Flexors
  12. Vector Fields Autonomous Control for Assistive Mobile Robots
  13. Between Recognition and Abstraction
  14. Learning spaces in multi-stakeholder initiatives
  15. Expectations on Hierarchical Scales of Discourse
  16. Doing everything you can, but not (yet) getting it right
  17. Peter's positions: a diffractive analysis of authority in a year one classroom
  18. Tree diversity promotes functional dissimilarity and maintains functional richness despite species loss in predator assemblages
  19. Local lens for SDG implementation: lessons from bottom-up approaches in Africa
  20. Modelling of a servo piezo mechanical hydraulic actuator and its feed-forward control
  21. Exploring feedback and student characteristics relevant for personalizing feedback strategies
  22. Implicit processes in moral decision making: Why milliseconds matter
  23. Microstructure, mechanical properties and fracture behaviors of large-scale sand-cast Mg-3Y-2Gd-1Nd-0.4Zr alloy