LGAIDMSYOCFeb 5, 2022

Reinforcement learning for multi-item retrieval in the puzzle-based storage system

arXiv:2202.03424v124 citations
AI Analysis

This addresses the retrieval efficiency challenge in high-density warehouses for logistics and fast delivery services, representing an incremental improvement with domain-specific applications.

The paper tackled the multi-item retrieval problem in puzzle-based storage systems by developing a deep reinforcement learning algorithm, which yielded high-quality solutions and outperformed three state-of-the-art heuristic algorithms in numerical experiments.

Nowadays, fast delivery services have created the need for high-density warehouses. The puzzle-based storage system is a practical way to enhance the storage density, however, facing difficulties in the retrieval process. In this work, a deep reinforcement learning algorithm, specifically the Double&Dueling Deep Q Network, is developed to solve the multi-item retrieval problem in the system with general settings, where multiple desired items, escorts, and I/O points are placed randomly. Additionally, we propose a general compact integer programming model to evaluate the solution quality. Extensive numerical experiments demonstrate that the reinforcement learning approach can yield high-quality solutions and outperforms three related state-of-the-art heuristic algorithms. Furthermore, a conversion algorithm and a decomposition framework are proposed to handle simultaneous movement and large-scale instances respectively, thus improving the applicability of the PBS system.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes