| 제목 | 다중 에이전트 강화 학습을 이용한 트랜스포터 혼잡 회피 경로 계획 최적화 |
|---|---|
| Title | Multi-Agent Reinforcement Learning for Optimizing Path Planning of Transporters Considering the Congestion |
| 저자 | 윤성재* (한양대학교 산업공학과) |
| Author | Seong Jae * (Department of Industrial Engineering, Hanyang Universi) |
| Bibliography | Journal of Logistics Science & Technology, 5(4),62~86, 2024, |
| DOI | 10.23178/jlst.5.4.202412.005 |
| Key Words | Distribution center, Multi-agent reinforcement learning, Dynamic path planning, Transporter, Congestion |
| Abstract | Advanced mega distribution centers(mega DCs) equipped with cutting-edge technologies are essential for enabling intelligent logistics operations. However, the efficient management of large-scale mega DCs with a dynamic array of autonomous transportation devices presents complexities that traditional path planning approaches struggle to address. To overcome these challenges, this study proposes an innovative path planning framework that integrates Multi-Agent Reinforcement Learning (MARL) with supplementary learning techniques to facilitate accelerated and stable training. This framework incorporates a specialized reward schema alongside auxiliary methodologies aimed at optimizing system-wide performance. Initially, we train MARL networks within a controlled, small-scale environment, focusing on path optimization for a limited number of transportation agents to validate efficiency. The trained model parameters are then leveraged as initial conditions for deployment in a larger-scale environment, thus expediting adaptation. Additionally, we employ a curriculum learning approach, segmenting the training process into levels of progressive difficulty to enhance convergence in complex, large-scale scenarios. Empirical results demonstrate that the proposed approach effectively mitigates operational challenges such as collisions, congestion, and deadlock, leading to significant improvements in overall system performance. |
| PDF download | JM_5[4]-P62~86.pdf |