Movable Antennas Assisted Air-Ground Collaborative Network: A DRL Approach for Uplink Sum-Rate Maximization

The deployment of movable antenna (MA) at base station (BS) within air-ground collaborative network constitutes a pivotal enhancement for Internet of things (IoT) wireless communications, as BS-mounted MAs dynamically reconfigure channel propagation conditions through antenna repositioning. Specifically, unmanned aerial vehicle (UAV) mobility enables extended service coverage while BS-deployed MA significantly enhances channel conditions through antenna position relocation. In this paper, we investigate a joint MA position, receive beamforming design at the BS, and UAV trajectory design problem to maximize the uplink sum-rate in the MAs assisted air-ground collaborative (MA-AGC) network. Given that the problem is non-convex and hard to solve by the traditional methods, we convert it into a Markov decision process (MDP) and solve it using a deep reinforcement learning (DRL) approach based on the multi-agent proximal policy optimization (MAPPO) collaborative framework. Simulation results have demonstrated that the proposed approach outperforms existing classical baseline methods in maximizing the uplink sum-rate.