Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

ACA: Automatic search strategy for radioactive source

  • Jianwen Huo (School of Information Engineering, Southwest University of Science and Technology) ;
  • Xulin Hu (School of Information Engineering, Southwest University of Science and Technology) ;
  • Junling Wang (School of National Defense Science, Southwest University of Science and Technology) ;
  • Li Hu (School of Information Engineering, Southwest University of Science and Technology)
  • Received : 2022.11.26
  • Accepted : 2023.05.14
  • Published : 2023.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

Nowadays, mobile robots have been used to search for uncontrolled radioactive source in indoor environments to avoid radiation exposure for technicians. However, in the indoor environments, especially in the presence of obstacles, how to make the robots with limited sensing capabilities automatically search for the radioactive source remains a major challenge. Also, the source search efficiency of robots needs to be further improved to meet practical scenarios such as limited exploration time. This paper proposes an automatic source search strategy, abbreviated as ACA: the location of source is estimated by a convolutional neural network (CNN), and the path is planned by the A-star algorithm. First, the search area is represented as an occupancy grid map. Then, the radiation dose distribution of the radioactive source in the occupancy grid map is obtained by Monte Carlo (MC) method simulation, and multiple sets of radiation data are collected through the eight neighborhood self-avoiding random walk (ENSAW) algorithm as the radiation data set. Further, the radiation data set is fed into the designed CNN architecture to train the network model in advance. When the searcher enters the search area where the radioactive source exists, the location of source is estimated by the network model and the search path is planned by the A-star algorithm, and this process is iterated continuously until the searcher reaches the location of radioactive source. The experimental results show that the average number of radiometric measurements and the average number of moving steps of the ACA algorithm are only 2.1% and 33.2% of those of the gradient search (GS) algorithm in the indoor environment without obstacles. In the indoor environment shielded by concrete walls, the GS algorithm fails to search for the source, while the ACA algorithm successfully searches for the source with fewer moving steps and sparse radiometric data.

Keywords

Acknowledgement

This research was funded by the National Natural Science Foundation of China (No.12205245, No.12175187), Natural Science Foundation of Sichuan Province (No. 2023NSFSC1437), Research Fund of Southwest University of Science and Technology (No. 22zx7109).

References

  1. IAEA Incident and Trafficking Database (ITDB), Incidents of nuclear and other radioactive material out of regulatory control, Available online: https://www.iaea.org/sites/default/fifiles/22/01/itdb-factsheet.pdf. (Accessed 17 November 2022).
  2. A.H.W. Liu, Simulation and Implementation of Distributed Sensor Network for Radiation Detection, California Institute of Technology, 2010.
  3. N.S.V. Rao, M. Shankar, J.C. Chin, D.K. Yau, S. Srivathsan, S.S. Iyengar, Identification of Low-Level Point Radiation Sources Using a Sensor Network. 2008 International Conference on Information Processing in Sensor Networks (IPSN), IEEE, 2008, pp. 493-504, 2008.
  4. J.W. Howse, L.O. Ticknor, K.R. Muske, Least squares estimation techniques for position tracking of radioactive sources, Automatica 37 (11) (2001) 1727-1737. https://doi.org/10.1016/S0005-1098(01)00134-0
  5. Y. Huang, J. Benesty, G.W. Elko, R.M. Mersereati, Real-time passive source localization: a practical linear-correction least-squares approach, IEEE Trans. Speech Audio Process. 9 (8) (2001) 943-956. https://doi.org/10.1109/89.966097
  6. A. Gunatilaka, B. Ristic, R. Gailis, On Localisation of a Radiological Point Source. 2007 Information, Decision and Control, IEEE, 2007, pp. 236-241, 2007.
  7. E. Bai, A. Heifetz, P. Raptis, S. Dasgupta, R. Mudumbai, Maximum likelihood localization of radioactive sources against a highly fluctuating background, IEEE Trans. Nucl. Sci. 62 (6) (2015) 3274-3282. https://doi.org/10.1109/TNS.2015.2497327
  8. H.E. Baidoo-Williams, Maximum Likelihood Localization of Radiation Sources with Unknown Source Intensity, 2016 arXiv preprint arXiv:1608.00427.
  9. J. Huo, M. Liu, K.A. Neusypin, H. Liu, M. Guo, Y. Xiao, Autonomous search of radioactive sources through mobile robots, Sensors 20 (12) (2020) 3461.
  10. Y. Liu, Y. Xuan, D. Zhang, S. Zou, Localizing unknown radiation sources by unscented particle filtering based on divide-and-conquer sampling, J. Nucl. Sci. Technol. (2022) 1-13, 2022.
  11. W. Gao, W. Wang, H. Zhu, G. Huang, D. Wu, Z. Du, Robust radiation sources localization based on the peak suppressed particle filter for mixed multimodal environments, Sensors 18 (11) (2018) 3784.
  12. M.R. Morelande, B. Ristic, Radiological source detection and localisation using Bayesian techniques, IEEE Trans. Signal Process. 57 (11) (2009) 4220-4231. https://doi.org/10.1109/TSP.2009.2026618
  13. A. West, I. Tsitsimpelis, M. Licata, A. Jazbec, L. Snoj, M.J. Joyce, B. Lennox, Use of Gaussian process regression for radiation mapping of a nuclear reactor with a mobile robot, Sci. Rep. 11 (1) (2021) 1-11. https://doi.org/10.1038/s41598-020-79139-8
  14. X. Xie, J. Cai, Z. Tang, The reconstruction of 3D radiation field based on sparse measurement data, Ann. Nucl. Energy 179 (2022), 109391.
  15. H. Tomita, S. Hara, A. Mukai, K. Yamagishi, H. Ebi, K. Shimazoe, Y. Tamura, H. Woo, H. Takahashi, H. Asama, F. Ishida, E. Takada, J. Kawarabayashi, K. Tanabe, K. Kamada, Path-planning system for radioisotope identification devices using 4p gamma imaging based on random forest analysis, Sensors 22 (12) (2022) 4325.
  16. M.S. Lee, M. Hanczor, J. Chu, Z. He, N. Michael, R. Whittaker, 3-d Volumetric Gamma-Ray Imaging and Source Localization with a Mobile Robot, 2018 arXiv preprint arXiv:1802.06072.
  17. Z. Liu, S. Abbaszadeh, Double Q-learning for radiation source detection, Sensors 19 (4) (2019) 960.
  18. A. Fathi, S.F. Masoudi, Lost gamma source detection algorithm based on convolutional neural network, Nucl. Eng. Technol. 53 (11) (2021) 3764-3771. https://doi.org/10.1016/j.net.2021.05.016
  19. Y. Zhao, B. Chen, X.H. Wang, Z. Zhu, Y. Wang, G. Cheng, Y. Liu, A deep reinforcement learning based searching method for source localization, Inf. Sci. 588 (2022) 67-81. https://doi.org/10.1016/j.ins.2021.12.041
  20. P. Proctor, C. Teuscher, A. Hecht, M. Osinski, Proximal policy optimization for radiation source search, Journal of Nuclear Engineering 2 (4) (2021) 368-397. https://doi.org/10.3390/jne2040029
  21. J. Chen, C. Tan, R. Mo, H. Zhang, G. Cai, H. Li, Research on path planning of three-neighbor search A* algorithm combined with artificial potential field, Int. J. Adv. Rob. Syst. 18 (3) (2021), 17298814211026449.
  22. Y. Ji, Y. Zhao, B. Chen, Z. Zhu, Y. Liu, H. Zhu, S. Qiu, Source searching in unknown obstructed environments through source estimation, target determination, and path planning, Build. Environ. 221 (2022), 109266.
  23. S. Agostinelli, J. Allison, K.A. Amako, J. Apostolakis, H. Araujo, P. Arce, Geant4 Collaboration., GEANT4da simulation toolkit, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 506 (3) (2003) 250-303. https://doi.org/10.1016/S0168-9002(03)01368-8
  24. J.F. Briesmeister, MCNPTM-A General Monte Carlo N-Particle Transport Code, in: Version 4C, LA-13709-M, vol. 2, Los Alamos National Laboratory, 2000.
  25. A. Ferrari, J. Ranft, P.R. Sala, A. Fasso, FLUKA: A Multi-Particle Transport Code (Program Version 2005), Cern, 2005.
  26. M. Bousquet-Melou, On the importance sampling of self-avoiding walks, Combinator. Probab. Comput. 23 (5) (2014) 725-748. https://doi.org/10.1017/S0963548313000643
  27. X. Hu, J. Huo, J. Wang, L. Hu, Y. Xiao, Research on a localization method of multiple unknown gamma radioactive sources, Ann. Nucl. Energy 177 (2022), 109302.
  28. A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, Commun. ACM 60 (6) (2017) 84-90. https://doi.org/10.1145/3065386
  29. K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014 arXiv preprint arXiv:1409.1556.
  30. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (1) (2014) 1929-1958.
  31. N.S.V. Rao, On performance of path planning algorithms in unknown terrains, ORSA J. Comput. 4 (2) (1992) 218-224. https://doi.org/10.1287/ijoc.4.2.218
  32. N.S.V. Rao, S. Kareti, W. Shi, S.S. Iyengar, Robot Navigation in Unknown Terrains: Introductory Survey of Non-heuristic Algorithms, Oak Ridge National Lab., TN (United States), 1993.
  33. M. Ling, J. Huo, G.V. Moiseev, L. Hu, Y. Xiao, Multi-robot collaborative radioactive source search based on particle fusion and adaptive step size, Ann. Nucl. Energy 173 (2022), 109104.