Semantic-Driven Multi-UAV Cooperative Communication With Joint Positioning and Resource Allocation

Semantic communication represents a new paradigm for sixth-generation wireless networks that prioritizes meaning-centric transmission. Unmanned aerial vehicles (UAVs) provide deployment flexibility and line-of-sight connectivity for coverage. The integration of these technologies presents challenges in the optimization of UAV deployment, radio resources, and semantic content fidelity. This paper proposes a framework for multi-UAV-enabled semantic communication that uses coordinated multipoint transmission. We formulate a problem to maximize the sum Quality of Experience (QoE) of all users by optimizing UAV positioning, cooperative beamforming, and semantic compression ratios, which results in a mixed-integer nonlinear programming problem. To solve this problem, we develop a hybrid alternating learning and optimization (HALO) algorithm. HALO decomposes the problem, using proximal policy optimization for discrete semantic compression decisions and an alternating optimization method for the continuous UAV positioning and beamforming variables. Simulation results show that the proposed framework achieves QoE improvements over benchmark methods, which validates the benefits of joint optimization in semantic-aware UAV networks.