The electromagnetic environment is increasingly complex and changeable, and radar needs to meet the execution requirements of various tasks. Modern radars should improve their intelligence level and have the ability to learn independently in dynamic countermeasures. It can make the radar countermeasure strategy change from the traditional fixed anti-interference strategy to dynamically and independently implementing an efficient anti-interference strategy. Aiming at the performance optimization of target tracking in the scene where multiple signals coexist, we propose a countermeasure method of cognitive radar based on a deep Q-learning network. In this paper, we analyze the tracking performance of this method and the Markov Decision Process under the triangular frequency sweeping interference, respectively. The simulation results show that reinforcement learning has substantial autonomy and adaptability for solving such problems.
Yong TIAN
University of Electronic Science and Technology of China
Peng WANG
University of Electronic Science and Technology of China
Xinyue HOU
University of Electronic Science and Technology of China
Junpeng YU
University of Electronic Science and Technology of China
Xiaoyan PENG
University of Electronic Science and Technology of China
Hongshu LIAO
University of Electronic Science and Technology of China
Lin GAO
University of Electronic Science and Technology of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yong TIAN, Peng WANG, Xinyue HOU, Junpeng YU, Xiaoyan PENG, Hongshu LIAO, Lin GAO, "A Deep Q-Network Based Intelligent Decision-Making Approach for Cognitive Radar" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 4, pp. 719-726, April 2022, doi: 10.1587/transfun.2021EAP1072.
Abstract: The electromagnetic environment is increasingly complex and changeable, and radar needs to meet the execution requirements of various tasks. Modern radars should improve their intelligence level and have the ability to learn independently in dynamic countermeasures. It can make the radar countermeasure strategy change from the traditional fixed anti-interference strategy to dynamically and independently implementing an efficient anti-interference strategy. Aiming at the performance optimization of target tracking in the scene where multiple signals coexist, we propose a countermeasure method of cognitive radar based on a deep Q-learning network. In this paper, we analyze the tracking performance of this method and the Markov Decision Process under the triangular frequency sweeping interference, respectively. The simulation results show that reinforcement learning has substantial autonomy and adaptability for solving such problems.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAP1072/_p
Copy
@ARTICLE{e105-a_4_719,
author={Yong TIAN, Peng WANG, Xinyue HOU, Junpeng YU, Xiaoyan PENG, Hongshu LIAO, Lin GAO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Deep Q-Network Based Intelligent Decision-Making Approach for Cognitive Radar},
year={2022},
volume={E105-A},
number={4},
pages={719-726},
abstract={The electromagnetic environment is increasingly complex and changeable, and radar needs to meet the execution requirements of various tasks. Modern radars should improve their intelligence level and have the ability to learn independently in dynamic countermeasures. It can make the radar countermeasure strategy change from the traditional fixed anti-interference strategy to dynamically and independently implementing an efficient anti-interference strategy. Aiming at the performance optimization of target tracking in the scene where multiple signals coexist, we propose a countermeasure method of cognitive radar based on a deep Q-learning network. In this paper, we analyze the tracking performance of this method and the Markov Decision Process under the triangular frequency sweeping interference, respectively. The simulation results show that reinforcement learning has substantial autonomy and adaptability for solving such problems.},
keywords={},
doi={10.1587/transfun.2021EAP1072},
ISSN={1745-1337},
month={April},}
Copy
TY - JOUR
TI - A Deep Q-Network Based Intelligent Decision-Making Approach for Cognitive Radar
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 719
EP - 726
AU - Yong TIAN
AU - Peng WANG
AU - Xinyue HOU
AU - Junpeng YU
AU - Xiaoyan PENG
AU - Hongshu LIAO
AU - Lin GAO
PY - 2022
DO - 10.1587/transfun.2021EAP1072
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2022
AB - The electromagnetic environment is increasingly complex and changeable, and radar needs to meet the execution requirements of various tasks. Modern radars should improve their intelligence level and have the ability to learn independently in dynamic countermeasures. It can make the radar countermeasure strategy change from the traditional fixed anti-interference strategy to dynamically and independently implementing an efficient anti-interference strategy. Aiming at the performance optimization of target tracking in the scene where multiple signals coexist, we propose a countermeasure method of cognitive radar based on a deep Q-learning network. In this paper, we analyze the tracking performance of this method and the Markov Decision Process under the triangular frequency sweeping interference, respectively. The simulation results show that reinforcement learning has substantial autonomy and adaptability for solving such problems.
ER -