Beamforming design and trajectory optimization for learning-based multi-UAV-assisted integrated sensing and communication systems

The integrated sensing and communication (ISAC) technology based on unmanned aerial vehicles (UAVs) can improve spectrum efficiency. ISAC enable the sharing of physical infrastructure for sensing and communication in sixth-generation (6G) wireless communication systems. However, existing studies mainly provide low-latency services from an overall perspective and cannot guarantee the high-quality experience of individual user devices. Therefore, we have studied a UAV-assisted ISAC framework, in which the UAV is equipped with a vertically placed uniform linear array (ULA). The UAV transmits combined information sensing signals, communicates with multiple users, and simultaneously detects ground targets. We have defined a new metric called the average rate ratio to reflect the users’ experience. Considering of the quality of service for communication and sensing, the problem is formulated to maximize the system’s average rate ratio by jointly optimizing communication and sensing beamforming as well as the UAV trajectory. Since this problem is a mixed-integer non-convex programming problem and difficult to solve within polynomial time, we have proposed an alternating optimization algorithm (AOA). This algorithm utilizes multiple learning agents to find effective strategies from experience, while ensuring communication and sensing performance, and finally performs alternating optimization. Numerical results verify the superiority and the effectiveness of the designed algorithm.