Bayesian Active Inference for Intelligent UAV Anti-Jamming and Adaptive Trajectory Planning

TL;DR

This paper introduces a hierarchical Bayesian Active Inference framework enabling UAVs to adaptively plan trajectories and counteract jamming in real-time, improving communication resilience and operational efficiency.

Contribution

The paper presents a novel Bayesian Active Inference approach for UAV trajectory planning under jamming, integrating expert demonstrations with probabilistic modeling for online adaptation.

Findings

Achieves near-expert performance in jamming scenarios

Reduces communication interference significantly

Maintains robustness in dynamic environments

Abstract

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.