Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning
Cognitive radar automatically adjusts its waveform via ceaseless interaction with the environment and learning from the experience. Compared with the linear frequency modulation (LFM) that has been commonly adopted in cognitive radars, the nonlinear FM (NLFM) signal has more flexible frequency varia...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838705/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207057343578112 |
|---|---|
| author | Peikun Zhu Xu Si Jiachen Han Jing Liang |
| author_facet | Peikun Zhu Xu Si Jiachen Han Jing Liang |
| author_sort | Peikun Zhu |
| collection | DOAJ |
| description | Cognitive radar automatically adjusts its waveform via ceaseless interaction with the environment and learning from the experience. Compared with the linear frequency modulation (LFM) that has been commonly adopted in cognitive radars, the nonlinear FM (NLFM) signal has more flexible frequency variation and small time delay–Doppler coupling. In this work, we propose an NLFM cognitive radar based on reinforcement learning for target sensing. Specifically, a radar waveform selection framework is proposed via the interactive multimodel. It embraces the Riccati equation and Riccati-like iterative calculations to obtain the prediction error covariance (PEC) and the prediction Bayesian Cramér–Rao lower bound (PBCRLB), respectively, which are used to guide the optimal waveform design. With PEC or PBCRLB, an entropy reward Q-learning method is also proposed for joint waveform parameter selection (JWPS) and pure waveform parameter selection from the NLFM library. Simulations show that both the time complexity and tracking accuracy of PEC-based Q-learning JWPS outperform that of the PBCRLB method. Furthermore, PXIe-5785 is utilized to construct a cognitive radar platform and conduct field experiments for nonlinear waveform sensing, which confirms that nonlinear waveforms are more effective than linear waveforms in target localization. |
| format | Article |
| id | doaj-art-d8ae7c015bbf4310af3a5e681beaf0b2 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-d8ae7c015bbf4310af3a5e681beaf0b22025-02-07T00:00:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184821483510.1109/JSTARS.2025.352865910838705Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement LearningPeikun Zhu0https://orcid.org/0000-0001-7482-2996Xu Si1https://orcid.org/0000-0003-1279-5667Jiachen Han2https://orcid.org/0000-0002-4811-5048Jing Liang3https://orcid.org/0000-0002-0860-6563School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaCognitive radar automatically adjusts its waveform via ceaseless interaction with the environment and learning from the experience. Compared with the linear frequency modulation (LFM) that has been commonly adopted in cognitive radars, the nonlinear FM (NLFM) signal has more flexible frequency variation and small time delay–Doppler coupling. In this work, we propose an NLFM cognitive radar based on reinforcement learning for target sensing. Specifically, a radar waveform selection framework is proposed via the interactive multimodel. It embraces the Riccati equation and Riccati-like iterative calculations to obtain the prediction error covariance (PEC) and the prediction Bayesian Cramér–Rao lower bound (PBCRLB), respectively, which are used to guide the optimal waveform design. With PEC or PBCRLB, an entropy reward Q-learning method is also proposed for joint waveform parameter selection (JWPS) and pure waveform parameter selection from the NLFM library. Simulations show that both the time complexity and tracking accuracy of PEC-based Q-learning JWPS outperform that of the PBCRLB method. Furthermore, PXIe-5785 is utilized to construct a cognitive radar platform and conduct field experiments for nonlinear waveform sensing, which confirms that nonlinear waveforms are more effective than linear waveforms in target localization.https://ieeexplore.ieee.org/document/10838705/Cognitive radar (CR)entropy reward Q-learning (ERQL)nonlinear frequency modulation (NLFM)target sensingwaveform selection |
| spellingShingle | Peikun Zhu Xu Si Jiachen Han Jing Liang Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Cognitive radar (CR) entropy reward Q-learning (ERQL) nonlinear frequency modulation (NLFM) target sensing waveform selection |
| title | Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning |
| title_full | Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning |
| title_fullStr | Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning |
| title_full_unstemmed | Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning |
| title_short | Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning |
| title_sort | nonlinear waveform sensing for cognitive radar based on reinforcement learning |
| topic | Cognitive radar (CR) entropy reward Q-learning (ERQL) nonlinear frequency modulation (NLFM) target sensing waveform selection |
| url | https://ieeexplore.ieee.org/document/10838705/ |
| work_keys_str_mv | AT peikunzhu nonlinearwaveformsensingforcognitiveradarbasedonreinforcementlearning AT xusi nonlinearwaveformsensingforcognitiveradarbasedonreinforcementlearning AT jiachenhan nonlinearwaveformsensingforcognitiveradarbasedonreinforcementlearning AT jingliang nonlinearwaveformsensingforcognitiveradarbasedonreinforcementlearning |