Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System
Intralogistics is a technology that optimizes, integrates, automates, and manages the logistics flow of goods within a logistics transportation and sortation center. As the demand for parcel transportation increases, many sortation systems have been developed. In general, the goal of sortation syste...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/12/3401 |
| _version_ | 1797565182657953792 |
|---|---|
| author | Ju-Bong Kim Ho-Bin Choi Gyu-Young Hwang Kwihoon Kim Yong-Geun Hong Youn-Hee Han |
| author_facet | Ju-Bong Kim Ho-Bin Choi Gyu-Young Hwang Kwihoon Kim Yong-Geun Hong Youn-Hee Han |
| author_sort | Ju-Bong Kim |
| collection | DOAJ |
| description | Intralogistics is a technology that optimizes, integrates, automates, and manages the logistics flow of goods within a logistics transportation and sortation center. As the demand for parcel transportation increases, many sortation systems have been developed. In general, the goal of sortation systems is to route (or sort) parcels correctly and quickly. We design an <i>n</i>-grid sortation system that can be flexibly deployed and used at intralogistics warehouse and develop a collaborative multi-agent reinforcement learning (RL) algorithm to control the behavior of emitters or sorters in the system. We present two types of RL agents, emission agents and routing agents, and they are trained to achieve the given sortation goals together. For the verification of the proposed system and algorithm, we implement them in a full-fledged cyber-physical system simulator and describe the RL agents’ learning performance. From the learning results, we present that the well-trained collaborative RL agents can optimize their performance effectively. In particular, the routing agents finally learn to route the parcels through their optimal paths, while the emission agents finally learn to balance the inflow and outflow of parcels. |
| first_indexed | 2024-03-10T19:08:21Z |
| format | Article |
| id | doaj.art-aaaaf8196b80484ebcd2bb36a22dbf36 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:08:21Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-aaaaf8196b80484ebcd2bb36a22dbf362023-11-20T04:01:02ZengMDPI AGSensors1424-82202020-06-012012340110.3390/s20123401Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation SystemJu-Bong Kim0Ho-Bin Choi1Gyu-Young Hwang2Kwihoon Kim3Yong-Geun Hong4Youn-Hee Han5Department of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaDepartment of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaDepartment of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaDepartment of Knowledge-Converged Super Brain Convergence Research, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaDepartment of Knowledge-Converged Super Brain Convergence Research, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaDepartment of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaIntralogistics is a technology that optimizes, integrates, automates, and manages the logistics flow of goods within a logistics transportation and sortation center. As the demand for parcel transportation increases, many sortation systems have been developed. In general, the goal of sortation systems is to route (or sort) parcels correctly and quickly. We design an <i>n</i>-grid sortation system that can be flexibly deployed and used at intralogistics warehouse and develop a collaborative multi-agent reinforcement learning (RL) algorithm to control the behavior of emitters or sorters in the system. We present two types of RL agents, emission agents and routing agents, and they are trained to achieve the given sortation goals together. For the verification of the proposed system and algorithm, we implement them in a full-fledged cyber-physical system simulator and describe the RL agents’ learning performance. From the learning results, we present that the well-trained collaborative RL agents can optimize their performance effectively. In particular, the routing agents finally learn to route the parcels through their optimal paths, while the emission agents finally learn to balance the inflow and outflow of parcels.https://www.mdpi.com/1424-8220/20/12/3401sortation systemn-grid sortation systemreinforcement learningmulti-agent reinforcement learning |
| spellingShingle | Ju-Bong Kim Ho-Bin Choi Gyu-Young Hwang Kwihoon Kim Yong-Geun Hong Youn-Hee Han Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System Sensors sortation system n-grid sortation system reinforcement learning multi-agent reinforcement learning |
| title | Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System |
| title_full | Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System |
| title_fullStr | Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System |
| title_full_unstemmed | Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System |
| title_short | Sortation Control Using Multi-Agent Deep Reinforcement Learning in <i>N</i>-Grid Sortation System |
| title_sort | sortation control using multi agent deep reinforcement learning in i n i grid sortation system |
| topic | sortation system n-grid sortation system reinforcement learning multi-agent reinforcement learning |
| url | https://www.mdpi.com/1424-8220/20/12/3401 |
| work_keys_str_mv | AT jubongkim sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem AT hobinchoi sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem AT gyuyounghwang sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem AT kwihoonkim sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem AT yonggeunhong sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem AT younheehan sortationcontrolusingmultiagentdeepreinforcementlearningininigridsortationsystem |