TANAGERS: Emergent Communication for UAVs as Flying Passive Radars

Driven by the compelling advantages of agility and cost-efficiency inherent in unmanned aerial vehicles (UAV s), this study introduces TANAGERS (emergenT communication for uA vs as flyinG passivE RadarS), an innovative communication-augmented multi-agent reinforcement learning algorithm (MARL) designed for the movement control of UAVs operating as flying passive radars in bistatic integrated sensing and communication scenarios. In this research, we employ the proposed MARL framework to address the sensing signal-to-noise ratio (SNR) maximization problem for targets within a given environment by leveraging signals from base stations, all while taking into account realistic communication channels between pairs of UAV s. Simulation results underscore the significant enhancement brought by our proposed algorithm in radar performance, as measured by the total achievable sensing SNR of the UAV s during their trajectory. The key strength lies in the algorithm's ability to learn a resilient communication protocol that effectively mitigates the stochastic and unreliable nature of channel links between UAV s.