Double Q-Learning for Radiation Source Detection
Anomalous radiation source detection in urban environments is challenging due to the complex nature of background radiation. When a suspicious area is determined, a radiation survey is usually carried out to search for anomalous radiation sources. To locate the source with high accuracy and in a sho...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/4/960 |
| _version_ | 1798024380541829120 |
|---|---|
| author | Zheng Liu Shiva Abbaszadeh |
| author_facet | Zheng Liu Shiva Abbaszadeh |
| author_sort | Zheng Liu |
| collection | DOAJ |
| description | Anomalous radiation source detection in urban environments is challenging due to the complex nature of background radiation. When a suspicious area is determined, a radiation survey is usually carried out to search for anomalous radiation sources. To locate the source with high accuracy and in a short time, different survey approaches have been studied such as scanning the area with fixed survey paths and data-driven approaches that update the survey path on the fly with newly acquired measurements. In this work, we propose reinforcement learning as a data-driven approach to conduct radiation detection tasks with no human intervention. A simulated radiation environment is constructed, and a convolutional neural network-based double Q-learning algorithm is built and tested for radiation source detection tasks. Simulation results show that the double Q-learning algorithm can reliably navigate the detector and reduce the searching time by at least 44% compared with traditional uniform search methods and gradient search methods. |
| first_indexed | 2024-04-11T18:02:38Z |
| format | Article |
| id | doaj.art-01e7b26a1a2140fb839e301fa1811081 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:02:38Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-01e7b26a1a2140fb839e301fa18110812022-12-22T04:10:26ZengMDPI AGSensors1424-82202019-02-0119496010.3390/s19040960s19040960Double Q-Learning for Radiation Source DetectionZheng Liu0Shiva Abbaszadeh1Department of Nuclear, Plasma, and Radiological Engineering, University of Illinois at Urbana-Champaign, 104 S Wright St, Urbana, IL 61801, USADepartment of Nuclear, Plasma, and Radiological Engineering, University of Illinois at Urbana-Champaign, 104 S Wright St, Urbana, IL 61801, USAAnomalous radiation source detection in urban environments is challenging due to the complex nature of background radiation. When a suspicious area is determined, a radiation survey is usually carried out to search for anomalous radiation sources. To locate the source with high accuracy and in a short time, different survey approaches have been studied such as scanning the area with fixed survey paths and data-driven approaches that update the survey path on the fly with newly acquired measurements. In this work, we propose reinforcement learning as a data-driven approach to conduct radiation detection tasks with no human intervention. A simulated radiation environment is constructed, and a convolutional neural network-based double Q-learning algorithm is built and tested for radiation source detection tasks. Simulation results show that the double Q-learning algorithm can reliably navigate the detector and reduce the searching time by at least 44% compared with traditional uniform search methods and gradient search methods.https://www.mdpi.com/1424-8220/19/4/960reinforcement learningradiation detectionsource searching |
| spellingShingle | Zheng Liu Shiva Abbaszadeh Double Q-Learning for Radiation Source Detection Sensors reinforcement learning radiation detection source searching |
| title | Double Q-Learning for Radiation Source Detection |
| title_full | Double Q-Learning for Radiation Source Detection |
| title_fullStr | Double Q-Learning for Radiation Source Detection |
| title_full_unstemmed | Double Q-Learning for Radiation Source Detection |
| title_short | Double Q-Learning for Radiation Source Detection |
| title_sort | double q learning for radiation source detection |
| topic | reinforcement learning radiation detection source searching |
| url | https://www.mdpi.com/1424-8220/19/4/960 |
| work_keys_str_mv | AT zhengliu doubleqlearningforradiationsourcedetection AT shivaabbaszadeh doubleqlearningforradiationsourcedetection |