ISAC-Enabled Low-Altitude Economy: Game-Theoretic Learning Empowered Techniques and Future Directions

Sixth-generation (6G) network has been emerging as a key support for the low-altitude economy (LAE), where the implementation of LAE is highly dependent on unmanned aerial vehicles (UAVs). Moreover, UAVs are expected to be airborne integrated sensing and communication (ISAC) platforms, thus forming the foundation for the ISAC-enabled LAE. In practice, the large-scale development of ISAC-enabled LAE relies on the collaboration of UAV swarms, where resource allocation and trajectory planning significantly determine the overall performance of ISAC-enabled LAE. However, how to optimize both resources and trajectories remains a key challenge due to the coupling of these two optimization problems in dynamic environments. Recently, game-theoretic learning approaches have gained attention due to their superiority in multi-agent dynamic interactions and distributed decision-making. Leveraging these advantages, game-theoretic learning approaches are promising for resolving the coupling problem inherent in the optimization of resources and trajectories for the ISAC-enabled LAE. In this article, the applications and challenges of ISAC-enabled LAE are first analyzed, emphasizing the significance of UAV swarm collaboration and the urgency of resource allocation and trajectory planning. Game-theoretic learning empowered approaches are then introduced, especially the multi-agent interactions for addressing the coupling problem. Subsequently, a game-theoretic deep reinforcement learning (DRL) approach is proposed, which focuses on integrating game theory’s decision mechanism with DRL’s adaptive capabilities to enable the joint optimization of resource allocation and trajectory planning for UAV swarms. Finally, the future research directions of ISAC-enabled LAE are introduced in detail.