A Research Review of Order Allocation in Robotic Mobile Fulfillment Systems
The rapid development of the e-commerce and logistics industries has placed increasing demands on picking efficiency in warehousing and distribution. In response, the application of Autonomous Mobile Robots (AMR) in the "goods-to-person" picking mode has become increasingly widespread. Thi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2025-06-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2025.03.100 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The rapid development of the e-commerce and logistics industries has placed increasing demands on picking efficiency in warehousing and distribution. In response, the application of Autonomous Mobile Robots (AMR) in the "goods-to-person" picking mode has become increasingly widespread. This paper presents a systematic review focusing on order allocation to AMRs within Robotic Mobile Fulfillment Systems (RMFS). Firstly, the concept of order allocation is clarified, followed by the construction of a theoretical framework that includes key variables, constraints, and optimization objectives. A classified discussion around this issue is then provided based on various characteristics. Next, to further elucidate related solution methods, this paper introduces research progress in order allocation and multi-robot task scheduling from various perspectives, such as classical optimization methods, heuristic and meta-heuristic algorithms, rule-based strategies, simulation optimization algorithms, as well as artificial intelligence and machine learning techniques. Subsequent discussions investigate factors affecting the efficiency of order allocation and summarizes the related core performance indexes. The paper further summarizes existing key challenges in this research field, such as real-time performance, multi-objective conflict, path conflict in multi-robot collaboration, dynamic uncertainty, and human factors. It concludes by proposing suggestions for future research directions, such as adaptive decision-making, multi-agent games, deep reinforcement learning combined with simulation platforms, and optimization for utilizing green energy. |
|---|---|
| ISSN: | 2096-5427 |