Active Inference Framework for Closed-Loop Sensing, Communication, and Control in UAV Systems

2025-09-17

AI Summary

Existing UAV-based integrated sensing, communication, and control (SCC) systems suffer from suboptimal resource utilization and degraded performance due to the decoupled design of sensing, communication, and control functionalities. To address this in 6G UAV scenarios, this paper proposes the first closed-loop SCC coordination framework grounded in active inference. We introduce a unified generative model wherein joint optimization of state estimation, sensing resource allocation, and control decision-making is achieved through variational free energy minimization. Action planning is guided by expected free energy, enabling adaptive resource scheduling and end-to-end control policy learning. Simulation results demonstrate that, compared to baseline methods, the proposed framework reduces control cost by 27.3% and sensing cost by 31.6%, significantly enhancing both system resource efficiency and control accuracy.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Integrated sensing and communication (ISAC) is a core technology for 6G, and its application to closed-loop sensing, communication, and control (SCC) enables various services. Existing SCC solutions often treat sensing and control separately, leading to suboptimal performance and resource usage. In this work, we introduce the active inference framework (AIF) into SCC-enabled unmanned aerial vehicle (UAV) systems for joint state estimation, control, and sensing resource allocation. By formulating a unified generative model, the problem reduces to minimizing variational free energy for inference and expected free energy for action planning. Simulation results show that both control cost and sensing cost are reduced relative to baselines.

Problem

• Optimizing joint state estimation and control in UAV systems
• Reducing sensing and control costs through integrated framework
• Improving resource allocation in sensing-communication-control loops

Innovation

• Active inference for joint state estimation
• Unified generative model minimizes variational energy
• Reduces control and sensing costs simultaneously