This paper proposes a novel unmanned aerial vehicle(UAV)-based illegal radio station(IRS) localization scheme, where the transmit power of the IRS, the channel model and the noise model are unknown to the UAV. A direc...This paper proposes a novel unmanned aerial vehicle(UAV)-based illegal radio station(IRS) localization scheme, where the transmit power of the IRS, the channel model and the noise model are unknown to the UAV. A direction-aware Q-learning algorithm is developed to process received signal strength(RSS) values collected by a directional antenna, as well as directions corresponding to the RSS values. This algorithm determines the direction the UAV flies towards and thereby finds the IRS. The proposed scheme is compared to two baseline schemes. One baseline locates the IRS by a UAV equipped with an omnidirectional antenna, where conventional Q-learning is exploited to process the measured RSS and determine the UAV's trajectory. The other baseline locates the IRS by a directional-antenna UAV, where the UAV flies towards the direction with respect to the maximum RSS value. Numerical results show that, especially for a low receive SNR, the proposed scheme can outperform the two baselines in terms of the localization efficiency, providing a smoother trajectory for the UAV.展开更多
基金supported by China NSF Grants(61631020)Fundamental Research Funds for the Central Universities(NP2018103,NE2017103,NC2017003)
文摘This paper proposes a novel unmanned aerial vehicle(UAV)-based illegal radio station(IRS) localization scheme, where the transmit power of the IRS, the channel model and the noise model are unknown to the UAV. A direction-aware Q-learning algorithm is developed to process received signal strength(RSS) values collected by a directional antenna, as well as directions corresponding to the RSS values. This algorithm determines the direction the UAV flies towards and thereby finds the IRS. The proposed scheme is compared to two baseline schemes. One baseline locates the IRS by a UAV equipped with an omnidirectional antenna, where conventional Q-learning is exploited to process the measured RSS and determine the UAV's trajectory. The other baseline locates the IRS by a directional-antenna UAV, where the UAV flies towards the direction with respect to the maximum RSS value. Numerical results show that, especially for a low receive SNR, the proposed scheme can outperform the two baselines in terms of the localization efficiency, providing a smoother trajectory for the UAV.