Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning
With the increasing complexity of patrol tasks, the use of deep reinforcement learning for collaborative coverage path planning (CPP) of multi-mobile robots has become a new hotspot. Taking into account the complexity of environmental factors and operational limitations, such as terrain obstacles an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/5/944 |
| _version_ | 1797264643947757568 |
|---|---|
| author | Jianjun Ni Yu Gu Guangyi Tang Chunyan Ke Yang Gu |
| author_facet | Jianjun Ni Yu Gu Guangyi Tang Chunyan Ke Yang Gu |
| author_sort | Jianjun Ni |
| collection | DOAJ |
| description | With the increasing complexity of patrol tasks, the use of deep reinforcement learning for collaborative coverage path planning (CPP) of multi-mobile robots has become a new hotspot. Taking into account the complexity of environmental factors and operational limitations, such as terrain obstacles and the scope of the task area, in order to complete the CPP task better, this paper proposes an improved K-Means clustering algorithm to divide the multi-robot task area. The improved K-Means clustering algorithm improves the selection of the first initial clustering point, which makes the clustering process more reasonable and helps to distribute tasks more evenly. Simultaneously, it introduces deep reinforcement learning with a dueling network structure to better deal with terrain obstacles and improves the reward function to guide the coverage process. The simulation experiments have confirmed the advantages of this method in terms of balanced task assignment, improvement in strategy quality, and enhancement of coverage efficiency. It can reduce path duplication and omission while ensuring coverage quality. |
| first_indexed | 2024-04-25T00:32:10Z |
| format | Article |
| id | doaj.art-648d0d2bd9a641ac8bcb7688b4de9a4d |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-25T00:32:10Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-648d0d2bd9a641ac8bcb7688b4de9a4d2024-03-12T16:42:41ZengMDPI AGElectronics2079-92922024-02-0113594410.3390/electronics13050944Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement LearningJianjun Ni0Yu Gu1Guangyi Tang2Chunyan Ke3Yang Gu4College of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, ChinaCollege of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, ChinaCollege of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, ChinaCollege of Information Science and Engineering, Hohai University, Changzhou 213200, ChinaCollege of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, ChinaWith the increasing complexity of patrol tasks, the use of deep reinforcement learning for collaborative coverage path planning (CPP) of multi-mobile robots has become a new hotspot. Taking into account the complexity of environmental factors and operational limitations, such as terrain obstacles and the scope of the task area, in order to complete the CPP task better, this paper proposes an improved K-Means clustering algorithm to divide the multi-robot task area. The improved K-Means clustering algorithm improves the selection of the first initial clustering point, which makes the clustering process more reasonable and helps to distribute tasks more evenly. Simultaneously, it introduces deep reinforcement learning with a dueling network structure to better deal with terrain obstacles and improves the reward function to guide the coverage process. The simulation experiments have confirmed the advantages of this method in terms of balanced task assignment, improvement in strategy quality, and enhancement of coverage efficiency. It can reduce path duplication and omission while ensuring coverage quality.https://www.mdpi.com/2079-9292/13/5/944coverage path planningdeep reinforcement learningdueling networkimproved K-Means clustering algorithmmulti-mobile robots |
| spellingShingle | Jianjun Ni Yu Gu Guangyi Tang Chunyan Ke Yang Gu Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning Electronics coverage path planning deep reinforcement learning dueling network improved K-Means clustering algorithm multi-mobile robots |
| title | Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning |
| title_full | Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning |
| title_fullStr | Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning |
| title_full_unstemmed | Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning |
| title_short | Cooperative Coverage Path Planning for Multi-Mobile Robots Based on Improved K-Means Clustering and Deep Reinforcement Learning |
| title_sort | cooperative coverage path planning for multi mobile robots based on improved k means clustering and deep reinforcement learning |
| topic | coverage path planning deep reinforcement learning dueling network improved K-Means clustering algorithm multi-mobile robots |
| url | https://www.mdpi.com/2079-9292/13/5/944 |
| work_keys_str_mv | AT jianjunni cooperativecoveragepathplanningformultimobilerobotsbasedonimprovedkmeansclusteringanddeepreinforcementlearning AT yugu cooperativecoveragepathplanningformultimobilerobotsbasedonimprovedkmeansclusteringanddeepreinforcementlearning AT guangyitang cooperativecoveragepathplanningformultimobilerobotsbasedonimprovedkmeansclusteringanddeepreinforcementlearning AT chunyanke cooperativecoveragepathplanningformultimobilerobotsbasedonimprovedkmeansclusteringanddeepreinforcementlearning AT yanggu cooperativecoveragepathplanningformultimobilerobotsbasedonimprovedkmeansclusteringanddeepreinforcementlearning |