An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments
Autonomous radiation source detection has long been studied for radiation emergencies. Compared to conventional data-driven or path planning methods, deep reinforcement learning shows a strong capacity in source detection while still lacking the generalized ability to the geometry in unknown environ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573322004429 |
| _version_ | 1797955422630445056 |
|---|---|
| author | Hao Hu Jiayue Wang Ai Chen Yang Liu |
| author_facet | Hao Hu Jiayue Wang Ai Chen Yang Liu |
| author_sort | Hao Hu |
| collection | DOAJ |
| description | Autonomous radiation source detection has long been studied for radiation emergencies. Compared to conventional data-driven or path planning methods, deep reinforcement learning shows a strong capacity in source detection while still lacking the generalized ability to the geometry in unknown environments. In this work, the detection task is decomposed into two subtasks: exploration and localization. A hierarchical control policy (HC) is proposed to perform the subtasks at different stages. The low-level controller learns how to execute the individual subtasks by deep reinforcement learning, and the high-level controller determines which subtasks should be executed at the current stage. In experimental tests under different geometrical conditions, HC achieves the best performance among the autonomous decision policies. The robustness and generalized ability of the hierarchy have been demonstrated. |
| first_indexed | 2024-04-10T23:34:02Z |
| format | Article |
| id | doaj.art-7f5b1e75fe934115a5e243ec7e98ebc0 |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-04-10T23:34:02Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-7f5b1e75fe934115a5e243ec7e98ebc02023-01-12T04:18:40ZengElsevierNuclear Engineering and Technology1738-57332023-01-01551285294An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environmentsHao Hu0Jiayue Wang1Ai Chen2Yang Liu3Sino-French Institute of Nuclear Engineering and Technology, Sun Yat-Sen University, Daxue Raod, Zhuhai, 519082, ChinaGuangdong Environmental Radiation Monitoring Center, Guangzhou Dadao Nan, Guangzhou, 510300, ChinaGuangdong Environmental Radiation Monitoring Center, Guangzhou Dadao Nan, Guangzhou, 510300, ChinaSino-French Institute of Nuclear Engineering and Technology, Sun Yat-Sen University, Daxue Raod, Zhuhai, 519082, China; Corresponding author. Sino-French Institute of Nuclear Engineering and Technology, Sun Yat-Sen University, Zhuhai, 519082, China.Autonomous radiation source detection has long been studied for radiation emergencies. Compared to conventional data-driven or path planning methods, deep reinforcement learning shows a strong capacity in source detection while still lacking the generalized ability to the geometry in unknown environments. In this work, the detection task is decomposed into two subtasks: exploration and localization. A hierarchical control policy (HC) is proposed to perform the subtasks at different stages. The low-level controller learns how to execute the individual subtasks by deep reinforcement learning, and the high-level controller determines which subtasks should be executed at the current stage. In experimental tests under different geometrical conditions, HC achieves the best performance among the autonomous decision policies. The robustness and generalized ability of the hierarchy have been demonstrated.http://www.sciencedirect.com/science/article/pii/S1738573322004429Radiation source detectionDeep reinforcement learningHierarchical learning |
| spellingShingle | Hao Hu Jiayue Wang Ai Chen Yang Liu An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments Nuclear Engineering and Technology Radiation source detection Deep reinforcement learning Hierarchical learning |
| title | An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| title_full | An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| title_fullStr | An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| title_full_unstemmed | An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| title_short | An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| title_sort | autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments |
| topic | Radiation source detection Deep reinforcement learning Hierarchical learning |
| url | http://www.sciencedirect.com/science/article/pii/S1738573322004429 |
| work_keys_str_mv | AT haohu anautonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT jiayuewang anautonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT aichen anautonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT yangliu anautonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT haohu autonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT jiayuewang autonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT aichen autonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments AT yangliu autonomousradiationsourcedetectionpolicybasedondeepreinforcementlearningwithgeneralizedabilityinunknownenvironments |