Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning
With the advancement of technology in vehicle-road collaboration and autonomous driving, new commercial applications have surfaced. These include autonomous ride-hailing vehicles and unmanned delivery vehicles. As a result of the challenges presented by commercial applications, dispatching systems a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10528314/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849690110998609920 |
|---|---|
| author | Shupei Zhang Huapeng Shi Wei Zhang Ying Pang Pengju Sun |
| author_facet | Shupei Zhang Huapeng Shi Wei Zhang Ying Pang Pengju Sun |
| author_sort | Shupei Zhang |
| collection | DOAJ |
| description | With the advancement of technology in vehicle-road collaboration and autonomous driving, new commercial applications have surfaced. These include autonomous ride-hailing vehicles and unmanned delivery vehicles. As a result of the challenges presented by commercial applications, dispatching systems are moving towards being maintenance-free, centralized, multitasking, and real-time. Yet, most existing dispatching systems have been designed for single-task purposes and cannot tackle multitasking issues. Moreover, traditional optimization algorithms make it difficult to achieve timeliness in real-time changing traffic conditions. Therefore, this paper innovatively proposes a task allocation method based on Multi-Agent Reinforcement Learning (MARL). Firstly, this study introduces a classification model of task relationships through the binary assumption model of geographical areas and vehicles. Secondly, the study matches the classification model’s task cost state transition process with the Markov Decision Process, constructing a Multi-Agent Reinforcement Learning framework. Finally, the study constructs a simulation environment suitable for reinforcement learning based on Simulation of Urban Mobility (SUMO). Simulation results indicate that the task allocation system based on MARL can effectively improve the system’s overall efficiency by determining the order of task allocation and the matching relationships between tasks. |
| format | Article |
| id | doaj-art-95b01aa7910b41e0939b19bc309cf93e |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-95b01aa7910b41e0939b19bc309cf93e2025-08-20T03:21:26ZengIEEEIEEE Access2169-35362024-01-0112814538147010.1109/ACCESS.2024.339961010528314Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement LearningShupei Zhang0Huapeng Shi1https://orcid.org/0009-0002-2006-9032Wei Zhang2Ying Pang3Pengju Sun4School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaWith the advancement of technology in vehicle-road collaboration and autonomous driving, new commercial applications have surfaced. These include autonomous ride-hailing vehicles and unmanned delivery vehicles. As a result of the challenges presented by commercial applications, dispatching systems are moving towards being maintenance-free, centralized, multitasking, and real-time. Yet, most existing dispatching systems have been designed for single-task purposes and cannot tackle multitasking issues. Moreover, traditional optimization algorithms make it difficult to achieve timeliness in real-time changing traffic conditions. Therefore, this paper innovatively proposes a task allocation method based on Multi-Agent Reinforcement Learning (MARL). Firstly, this study introduces a classification model of task relationships through the binary assumption model of geographical areas and vehicles. Secondly, the study matches the classification model’s task cost state transition process with the Markov Decision Process, constructing a Multi-Agent Reinforcement Learning framework. Finally, the study constructs a simulation environment suitable for reinforcement learning based on Simulation of Urban Mobility (SUMO). Simulation results indicate that the task allocation system based on MARL can effectively improve the system’s overall efficiency by determining the order of task allocation and the matching relationships between tasks.https://ieeexplore.ieee.org/document/10528314/Combinatorial optimizationmulti-agent systemreinforcement learningsimulation of urban mobilitytask allocation |
| spellingShingle | Shupei Zhang Huapeng Shi Wei Zhang Ying Pang Pengju Sun Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning IEEE Access Combinatorial optimization multi-agent system reinforcement learning simulation of urban mobility task allocation |
| title | Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning |
| title_full | Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning |
| title_fullStr | Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning |
| title_full_unstemmed | Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning |
| title_short | Real-Time Multi-Vehicle Scheduling in Tasks With Dependency Relationships Using Multi-Agent Reinforcement Learning |
| title_sort | real time multi vehicle scheduling in tasks with dependency relationships using multi agent reinforcement learning |
| topic | Combinatorial optimization multi-agent system reinforcement learning simulation of urban mobility task allocation |
| url | https://ieeexplore.ieee.org/document/10528314/ |
| work_keys_str_mv | AT shupeizhang realtimemultivehicleschedulingintaskswithdependencyrelationshipsusingmultiagentreinforcementlearning AT huapengshi realtimemultivehicleschedulingintaskswithdependencyrelationshipsusingmultiagentreinforcementlearning AT weizhang realtimemultivehicleschedulingintaskswithdependencyrelationshipsusingmultiagentreinforcementlearning AT yingpang realtimemultivehicleschedulingintaskswithdependencyrelationshipsusingmultiagentreinforcementlearning AT pengjusun realtimemultivehicleschedulingintaskswithdependencyrelationshipsusingmultiagentreinforcementlearning |