Bayesian Active Inference for Intelligent UAV Anti-Jamming and Adaptive Trajectory Planning
This addresses the problem of adaptive and anti-jamming trajectory planning for UAVs in adversarial conditions, representing an incremental improvement over existing methods.
The paper tackles the problem of UAV trajectory planning under adversarial jamming by proposing a hierarchical framework using Bayesian Active Inference, which achieves near-expert performance, significantly reduces communication interference and mission cost compared to baselines, and maintains robust generalization in dynamic environments.
This paper proposes a hierarchical trajectory planning framework for UAVs operating under adversarial jamming conditions. Leveraging Bayesian Active Inference, the approach combines expert-generated demonstrations with probabilistic generative modeling to encode high-level symbolic planning, low-level motion policies, and wireless signal feedback. During deployment, the UAV performs online inference to anticipate interference, localize jammers, and adapt its trajectory accordingly, without prior knowledge of jammer locations. Simulation results demonstrate that the proposed method achieves near-expert performance, significantly reducing communication interference and mission cost compared to model-free reinforcement learning baselines, while maintaining robust generalization in dynamic environments.