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

2025-12-05

AI Summary

To address the insufficient trajectory planning robustness of unmanned aerial vehicles (UAVs) under adversarial communication jamming with unknown jammer locations, this paper proposes a Bayesian active inference–driven hierarchical adaptive framework. The framework integrates expert demonstrations with probabilistic generative modeling to enable closed-loop coupling between symbolic-level high-level path planning and low-level motion control, while leveraging real-time wireless signal feedback for online jamming prediction, jammer localization, and dynamic trajectory replanning. Crucially, it operates without prior knowledge of jammer positions, achieving jamming-resilient communication and minimal task cost in dynamic environments. Simulation results demonstrate that the method approaches expert-level performance, reducing communication outage rate by 42% and task cost by 35% compared to model-free reinforcement learning baselines. Moreover, it exhibits strong generalization capability and deployment stability.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Develops UAV trajectory planning under adversarial jamming conditions
• Enables online jammer localization without prior knowledge of locations
• Reduces communication interference and mission costs dynamically

Innovation

• Bayesian Active Inference for UAV trajectory planning
• Hierarchical framework combining expert demonstrations and probabilistic modeling
• Online inference for jammer localization and adaptive path adjustment