Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning
Global fruit production costs are increasing amid intensified labor shortages, driving heightened interest in robotic harvesting technologies. Although multi-arm coordination in harvesting robots is considered a highly promising solution to this issue, it introduces technical challenges in achieving...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Horticulturae |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-7524/11/1/88 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588342333538304 |
|---|---|
| author | Feng Xie Zhengwei Guo Tao Li Qingchun Feng Chunjiang Zhao |
| author_facet | Feng Xie Zhengwei Guo Tao Li Qingchun Feng Chunjiang Zhao |
| author_sort | Feng Xie |
| collection | DOAJ |
| description | Global fruit production costs are increasing amid intensified labor shortages, driving heightened interest in robotic harvesting technologies. Although multi-arm coordination in harvesting robots is considered a highly promising solution to this issue, it introduces technical challenges in achieving effective coordination. These challenges include mutual interference among multi-arm mechanical structures, task allocation across multiple arms, and dynamic operating conditions. This imposes higher demands on task coordination for multi-arm harvesting robots, requiring collision-free collaboration, optimization of task sequences, and dynamic re-planning. In this work, we propose a framework that models the task planning problem of multi-arm operation as a Markov game. First, considering multi-arm cooperative movement and picking sequence optimization, we employ a two-agent Markov game framework to model the multi-arm harvesting robot task planning problem. Second, we introduce a self-attention mechanism and a centralized training and execution strategy in the design and training of our deep reinforcement learning (DRL) model, thereby enhancing the model’s adaptability in dynamic and uncertain environments and improving decision accuracy. Finally, we conduct extensive numerical simulations in static environments; when the harvesting targets are set to 25 and 50, the execution time is reduced by 10.7% and 3.1%, respectively, compared to traditional methods. Additionally, in dynamic environments, both operational efficiency and robustness are superior to traditional approaches. The results underscore the potential of our approach to revolutionize multi-arm harvesting robotics by providing a more adaptive and efficient task planning solution. We will research improving the positioning accuracy of fruits in the future, which will make it possible to apply this framework to real robots. |
| format | Article |
| id | doaj-art-5435ee0123b548929f08f24065f07b1c |
| institution | Kabale University |
| issn | 2311-7524 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Horticulturae |
| spelling | doaj-art-5435ee0123b548929f08f24065f07b1c2025-01-24T13:34:44ZengMDPI AGHorticulturae2311-75242025-01-011118810.3390/horticulturae11010088Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement LearningFeng Xie0Zhengwei Guo1Tao Li2Qingchun Feng3Chunjiang Zhao4School of Agricultural Engineering, Jiangsu University, Zhenjiang 212000, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530000, ChinaGlobal fruit production costs are increasing amid intensified labor shortages, driving heightened interest in robotic harvesting technologies. Although multi-arm coordination in harvesting robots is considered a highly promising solution to this issue, it introduces technical challenges in achieving effective coordination. These challenges include mutual interference among multi-arm mechanical structures, task allocation across multiple arms, and dynamic operating conditions. This imposes higher demands on task coordination for multi-arm harvesting robots, requiring collision-free collaboration, optimization of task sequences, and dynamic re-planning. In this work, we propose a framework that models the task planning problem of multi-arm operation as a Markov game. First, considering multi-arm cooperative movement and picking sequence optimization, we employ a two-agent Markov game framework to model the multi-arm harvesting robot task planning problem. Second, we introduce a self-attention mechanism and a centralized training and execution strategy in the design and training of our deep reinforcement learning (DRL) model, thereby enhancing the model’s adaptability in dynamic and uncertain environments and improving decision accuracy. Finally, we conduct extensive numerical simulations in static environments; when the harvesting targets are set to 25 and 50, the execution time is reduced by 10.7% and 3.1%, respectively, compared to traditional methods. Additionally, in dynamic environments, both operational efficiency and robustness are superior to traditional approaches. The results underscore the potential of our approach to revolutionize multi-arm harvesting robotics by providing a more adaptive and efficient task planning solution. We will research improving the positioning accuracy of fruits in the future, which will make it possible to apply this framework to real robots.https://www.mdpi.com/2311-7524/11/1/88multi-arm harvesting robotstarget planningmultiple constraintsdeep reinforcement learning |
| spellingShingle | Feng Xie Zhengwei Guo Tao Li Qingchun Feng Chunjiang Zhao Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning Horticulturae multi-arm harvesting robots target planning multiple constraints deep reinforcement learning |
| title | Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning |
| title_full | Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning |
| title_fullStr | Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning |
| title_full_unstemmed | Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning |
| title_short | Dynamic Task Planning for Multi-Arm Harvesting Robots Under Multiple Constraints Using Deep Reinforcement Learning |
| title_sort | dynamic task planning for multi arm harvesting robots under multiple constraints using deep reinforcement learning |
| topic | multi-arm harvesting robots target planning multiple constraints deep reinforcement learning |
| url | https://www.mdpi.com/2311-7524/11/1/88 |
| work_keys_str_mv | AT fengxie dynamictaskplanningformultiarmharvestingrobotsundermultipleconstraintsusingdeepreinforcementlearning AT zhengweiguo dynamictaskplanningformultiarmharvestingrobotsundermultipleconstraintsusingdeepreinforcementlearning AT taoli dynamictaskplanningformultiarmharvestingrobotsundermultipleconstraintsusingdeepreinforcementlearning AT qingchunfeng dynamictaskplanningformultiarmharvestingrobotsundermultipleconstraintsusingdeepreinforcementlearning AT chunjiangzhao dynamictaskplanningformultiarmharvestingrobotsundermultipleconstraintsusingdeepreinforcementlearning |