Reinforcement-Learning-Based 2D Flow Control for Logistics Systems

Mingrui Yin; Chenxin Cai; Jie Liu

doi:10.1007/978-981-97-1010-2_19

Reinforcement-Learning-Based 2D Flow Control for Logistics Systems

Mingrui Yin^*
, Chenxin Cai
, Jie Liu

^*Corresponding author for this work

Faculty of Computing, Harbin Institute of Technology
International Research Institute for Artificial Intelligence, Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

To address large-scale challenges in current logistics systems, we present an logistics system employing a multi-agent framework grounded on an actuator network named Omniveyor. This design ensures real-time responsiveness and scalability in flow operations. Under the premise of centralized control, we employ Reinforcement Learning (RL) to efficiently control omni-wheel conveyors. Different from traditional path planning, our approach considers the entire platform as an agent, using the package state for observation. Proximal Policy Optimization (PPO) proves to be an effective algorithm for platform-wide control planning. Experimental results demonstrate the system’s capability to accurately deliver packages. Therefore, the RL algorithm allows the omni-wheel platform to autonomously learn and optimize package paths, circumventing the need for traditional controls or path planning methods.

Original language	English
Title of host publication	Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings
Editors	Lei Wang, Tie Qiu, Chi Lin, Xinbing Wang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	257-270
Number of pages	14
ISBN (Print)	9789819710096
DOIs	https://doi.org/10.1007/978-981-97-1010-2_19
State	Published - 2024
Externally published	Yes
Event	17th China Conference on Wireless Sensor Networks, CWSN 2023 - Dalian, China Duration: 13 Oct 2023 → 15 Oct 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1994 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	17th China Conference on Wireless Sensor Networks, CWSN 2023
Country/Territory	China
City	Dalian
Period	13/10/23 → 15/10/23

Keywords

Centralized control system
Logistics system
Reinforcement Learning

Access to Document

10.1007/978-981-97-1010-2_19

Cite this

Yin, M., Cai, C., & Liu, J. (2024). Reinforcement-Learning-Based 2D Flow Control for Logistics Systems. In L. Wang, T. Qiu, C. Lin, & X. Wang (Eds.), Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings (pp. 257-270). (Communications in Computer and Information Science; Vol. 1994 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-1010-2_19

@inproceedings{1db361e72baf4c30b730b63519c0330f,

title = "Reinforcement-Learning-Based 2D Flow Control for Logistics Systems",

abstract = "To address large-scale challenges in current logistics systems, we present an logistics system employing a multi-agent framework grounded on an actuator network named Omniveyor. This design ensures real-time responsiveness and scalability in flow operations. Under the premise of centralized control, we employ Reinforcement Learning (RL) to efficiently control omni-wheel conveyors. Different from traditional path planning, our approach considers the entire platform as an agent, using the package state for observation. Proximal Policy Optimization (PPO) proves to be an effective algorithm for platform-wide control planning. Experimental results demonstrate the system{\textquoteright}s capability to accurately deliver packages. Therefore, the RL algorithm allows the omni-wheel platform to autonomously learn and optimize package paths, circumventing the need for traditional controls or path planning methods.",

keywords = "Centralized control system, Logistics system, Reinforcement Learning",

author = "Mingrui Yin and Chenxin Cai and Jie Liu",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 17th China Conference on Wireless Sensor Networks, CWSN 2023 ; Conference date: 13-10-2023 Through 15-10-2023",

year = "2024",

doi = "10.1007/978-981-97-1010-2\_19",

language = "英语",

isbn = "9789819710096",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "257--270",

editor = "Lei Wang and Tie Qiu and Chi Lin and Xinbing Wang",

booktitle = "Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings",

address = "德国",

}

Yin, M, Cai, C & Liu, J 2024, Reinforcement-Learning-Based 2D Flow Control for Logistics Systems. in L Wang, T Qiu, C Lin & X Wang (eds), Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings. Communications in Computer and Information Science, vol. 1994 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 257-270, 17th China Conference on Wireless Sensor Networks, CWSN 2023, Dalian, China, 13/10/23. https://doi.org/10.1007/978-981-97-1010-2_19

Reinforcement-Learning-Based 2D Flow Control for Logistics Systems. / Yin, Mingrui; Cai, Chenxin; Liu, Jie.
Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings. ed. / Lei Wang; Tie Qiu; Chi Lin; Xinbing Wang. Springer Science and Business Media Deutschland GmbH, 2024. p. 257-270 (Communications in Computer and Information Science; Vol. 1994 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Reinforcement-Learning-Based 2D Flow Control for Logistics Systems

AU - Yin, Mingrui

AU - Cai, Chenxin

AU - Liu, Jie

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - To address large-scale challenges in current logistics systems, we present an logistics system employing a multi-agent framework grounded on an actuator network named Omniveyor. This design ensures real-time responsiveness and scalability in flow operations. Under the premise of centralized control, we employ Reinforcement Learning (RL) to efficiently control omni-wheel conveyors. Different from traditional path planning, our approach considers the entire platform as an agent, using the package state for observation. Proximal Policy Optimization (PPO) proves to be an effective algorithm for platform-wide control planning. Experimental results demonstrate the system’s capability to accurately deliver packages. Therefore, the RL algorithm allows the omni-wheel platform to autonomously learn and optimize package paths, circumventing the need for traditional controls or path planning methods.

AB - To address large-scale challenges in current logistics systems, we present an logistics system employing a multi-agent framework grounded on an actuator network named Omniveyor. This design ensures real-time responsiveness and scalability in flow operations. Under the premise of centralized control, we employ Reinforcement Learning (RL) to efficiently control omni-wheel conveyors. Different from traditional path planning, our approach considers the entire platform as an agent, using the package state for observation. Proximal Policy Optimization (PPO) proves to be an effective algorithm for platform-wide control planning. Experimental results demonstrate the system’s capability to accurately deliver packages. Therefore, the RL algorithm allows the omni-wheel platform to autonomously learn and optimize package paths, circumventing the need for traditional controls or path planning methods.

KW - Centralized control system

KW - Logistics system

KW - Reinforcement Learning

UR - https://www.scopus.com/pages/publications/85187716894

U2 - 10.1007/978-981-97-1010-2_19

DO - 10.1007/978-981-97-1010-2_19

M3 - 会议稿件

AN - SCOPUS:85187716894

SN - 9789819710096

T3 - Communications in Computer and Information Science

SP - 257

EP - 270

BT - Wireless Sensor Networks - 17th China Conference, CWSN 2023, Proceedings

A2 - Wang, Lei

A2 - Qiu, Tie

A2 - Lin, Chi

A2 - Wang, Xinbing

PB - Springer Science and Business Media Deutschland GmbH

T2 - 17th China Conference on Wireless Sensor Networks, CWSN 2023

Y2 - 13 October 2023 through 15 October 2023

ER -