The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning
Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligenc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/12/4316 |
| _version_ | 1797482545041899520 |
|---|---|
| author | Jiachen Yang Jingfei Ni Yang Li Jiabao Wen Desheng Chen |
| author_facet | Jiachen Yang Jingfei Ni Yang Li Jiabao Wen Desheng Chen |
| author_sort | Jiachen Yang |
| collection | DOAJ |
| description | Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks. In response to this requirement, this paper proposes a Residual-like Soft Actor Critic (R-SAC) algorithm for agricultural scenarios to realize safe obstacle avoidance and intelligent path planning of robots. In addition, in order to alleviate the time-consuming problem of exploration process of reinforcement learning, this paper proposes an offline expert experience pre-training method, which improves the training efficiency of reinforcement learning. Moreover, this paper optimizes the reward mechanism of the algorithm by using multi-step TD-error, which solves the probable dilemma during training. Experiments verify that our proposed method has stable performance in both static and dynamic obstacle environments, and is superior to other reinforcement learning algorithms. It is a stable and efficient path planning method and has visible application potential in agricultural robots. |
| first_indexed | 2024-03-09T22:33:55Z |
| format | Article |
| id | doaj.art-83c242c8315140909b16cc53f27f8a42 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:33:55Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-83c242c8315140909b16cc53f27f8a422023-11-23T18:51:28ZengMDPI AGSensors1424-82202022-06-012212431610.3390/s22124316The Intelligent Path Planning System of Agricultural Robot via Reinforcement LearningJiachen Yang0Jingfei Ni1Yang Li2Jiabao Wen3Desheng Chen4School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaAgricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks. In response to this requirement, this paper proposes a Residual-like Soft Actor Critic (R-SAC) algorithm for agricultural scenarios to realize safe obstacle avoidance and intelligent path planning of robots. In addition, in order to alleviate the time-consuming problem of exploration process of reinforcement learning, this paper proposes an offline expert experience pre-training method, which improves the training efficiency of reinforcement learning. Moreover, this paper optimizes the reward mechanism of the algorithm by using multi-step TD-error, which solves the probable dilemma during training. Experiments verify that our proposed method has stable performance in both static and dynamic obstacle environments, and is superior to other reinforcement learning algorithms. It is a stable and efficient path planning method and has visible application potential in agricultural robots.https://www.mdpi.com/1424-8220/22/12/4316reinforcement learningagricultural robotpath planningobstacle avoidanceintelligent controlInternet of Things |
| spellingShingle | Jiachen Yang Jingfei Ni Yang Li Jiabao Wen Desheng Chen The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning Sensors reinforcement learning agricultural robot path planning obstacle avoidance intelligent control Internet of Things |
| title | The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning |
| title_full | The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning |
| title_fullStr | The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning |
| title_full_unstemmed | The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning |
| title_short | The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning |
| title_sort | intelligent path planning system of agricultural robot via reinforcement learning |
| topic | reinforcement learning agricultural robot path planning obstacle avoidance intelligent control Internet of Things |
| url | https://www.mdpi.com/1424-8220/22/12/4316 |
| work_keys_str_mv | AT jiachenyang theintelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT jingfeini theintelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT yangli theintelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT jiabaowen theintelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT deshengchen theintelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT jiachenyang intelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT jingfeini intelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT yangli intelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT jiabaowen intelligentpathplanningsystemofagriculturalrobotviareinforcementlearning AT deshengchen intelligentpathplanningsystemofagriculturalrobotviareinforcementlearning |