Embodied intelligence-enhanced anti-jamming resource allocation for low-altitude communication networks

Uncrewed aerial vehicles (UAVs)-assisted low-altitude communication networks have emerged as a promising solution for extending air-to-ground communication coverage and services. However, UAV-assisted communications are highly susceptible to jamming attacks due to its high probability of line-of-sight links. In this paper, we design an embodied intelligence-enhanced low-altitude communication network under malicious jammers, where multiple UAVs act as embodied intelligent agents to collaborate and jointly optimize power allocation and spectrum allocation to minimize transmission delay, while guaranteeing quality of service requirements against jamming attacks. Considering the non-convex problem and highly dynamic wireless environments, we propose an embodied multiagent deep reinforcement learning (E-MA-DRL)-based intelligent resource allocation approach to jointly optimize the communication resource, where embodied intelligent agents (UAVs) sense communication states, learn to make decisions and perform resource allocation actions. To enhance learning efficiency and performance, we then design prioritized experience replay (PER) and transfer learning (TL) in a double deep Q-network (DDQN) algorithm, to smartly schedule the communication resource and reduce the effect of jamming attacks and inter-channel interference. Simulation results show that the proposed approach significantly reduces communication delay and improves the probability of successful transmission in low-altitude communication networks against jamming attacks.